Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目,它使游戏和模拟能够作为训练智能代理的环境。
您最多选择25个主题 主题必须以中文或者字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符
 
 
 
 
 

56 KiB

Table of Contents

mlagents_envs.env_utils

get_platform

get_platform()

returns the platform of the operating system : linux, darwin or win32

validate_environment_path

validate_environment_path(env_path: str) -> Optional[str]

Strip out executable extensions of the env_path

Arguments:

  • env_path: The path to the executable

launch_executable

launch_executable(file_name: str, args: List[str]) -> subprocess.Popen

Launches a Unity executable and returns the process handle for it.

Arguments:

  • file_name: the name of the executable
  • args: List of string that will be passed as command line arguments when launching the executable.

mlagents_envs.base_env

Python Environment API for the ML-Agents Toolkit The aim of this API is to expose Agents evolving in a simulation to perform reinforcement learning on. This API supports multi-agent scenarios and groups similar Agents (same observations, actions spaces and behavior) together. These groups of Agents are identified by their BehaviorName. For performance reasons, the data of each group of agents is processed in a batched manner. Agents are identified by a unique AgentId identifier that allows tracking of Agents across simulation steps. Note that there is no guarantee that the number or order of the Agents in the state will be consistent across simulation steps. A simulation steps corresponds to moving the simulation forward until at least one agent in the simulation sends its observations to Python again. Since Agents can request decisions at different frequencies, a simulation step does not necessarily correspond to a fixed simulation time increment.

DecisionStep Objects

class DecisionStep(NamedTuple)

Contains the data a single Agent collected since the last simulation step.

  • obs is a list of numpy arrays observations collected by the agent.
  • reward is a float. Corresponds to the rewards collected by the agent since the last simulation step.
  • agent_id is an int and an unique identifier for the corresponding Agent.
  • action_mask is an optional list of one dimensional array of booleans. Only available when using multi-discrete actions. Each array corresponds to an action branch. Each array contains a mask for each action of the branch. If true, the action is not available for the agent during this simulation step.

DecisionSteps Objects

class DecisionSteps(Mapping)

Contains the data a batch of similar Agents collected since the last simulation step. Note that all Agents do not necessarily have new information to send at each simulation step. Therefore, the ordering of agents and the batch size of the DecisionSteps are not fixed across simulation steps.

  • obs is a list of numpy arrays observations collected by the batch of agent. Each obs has one extra dimension compared to DecisionStep: the first dimension of the array corresponds to the batch size of the batch.
  • reward is a float vector of length batch size. Corresponds to the rewards collected by each agent since the last simulation step.
  • agent_id is an int vector of length batch size containing unique identifier for the corresponding Agent. This is used to track Agents across simulation steps.
  • action_mask is an optional list of two dimensional array of booleans. Only available when using multi-discrete actions. Each array corresponds to an action branch. The first dimension of each array is the batch size and the second contains a mask for each action of the branch. If true, the action is not available for the agent during this simulation step.

agent_id_to_index

 | @property
 | agent_id_to_index() -> Dict[AgentId, int]

Returns:

A Dict that maps agent_id to the index of those agents in this DecisionSteps.

__getitem__

 | __getitem__(agent_id: AgentId) -> DecisionStep

returns the DecisionStep for a specific agent.

Arguments:

  • agent_id: The id of the agent

Returns:

The DecisionStep

empty

 | @staticmethod
 | empty(spec: "BehaviorSpec") -> "DecisionSteps"

Returns an empty DecisionSteps.

Arguments:

  • spec: The BehaviorSpec for the DecisionSteps

TerminalStep Objects

class TerminalStep(NamedTuple)

Contains the data a single Agent collected when its episode ended.

  • obs is a list of numpy arrays observations collected by the agent.
  • reward is a float. Corresponds to the rewards collected by the agent since the last simulation step.
  • interrupted is a bool. Is true if the Agent was interrupted since the last decision step. For example, if the Agent reached the maximum number of steps for the episode.
  • agent_id is an int and an unique identifier for the corresponding Agent.

TerminalSteps Objects

class TerminalSteps(Mapping)

Contains the data a batch of Agents collected when their episode terminated. All Agents present in the TerminalSteps have ended their episode.

  • obs is a list of numpy arrays observations collected by the batch of agent. Each obs has one extra dimension compared to DecisionStep: the first dimension of the array corresponds to the batch size of the batch.
  • reward is a float vector of length batch size. Corresponds to the rewards collected by each agent since the last simulation step.
  • interrupted is an array of booleans of length batch size. Is true if the associated Agent was interrupted since the last decision step. For example, if the Agent reached the maximum number of steps for the episode.
  • agent_id is an int vector of length batch size containing unique identifier for the corresponding Agent. This is used to track Agents across simulation steps.

agent_id_to_index

 | @property
 | agent_id_to_index() -> Dict[AgentId, int]

Returns:

A Dict that maps agent_id to the index of those agents in this TerminalSteps.

__getitem__

 | __getitem__(agent_id: AgentId) -> TerminalStep

returns the TerminalStep for a specific agent.

Arguments:

  • agent_id: The id of the agent

Returns:

obs, reward, done, agent_id and optional action mask for a specific agent

empty

 | @staticmethod
 | empty(spec: "BehaviorSpec") -> "TerminalSteps"

Returns an empty TerminalSteps.

Arguments:

  • spec: The BehaviorSpec for the TerminalSteps

ActionTuple Objects

class ActionTuple(_ActionTupleBase)

An object whose fields correspond to actions of different types. Continuous and discrete actions are numpy arrays of type float32 and int32, respectively and are type checked on construction. Dimensions are of (n_agents, continuous_size) and (n_agents, discrete_size), respectively. Note, this also holds when continuous or discrete size is zero.

discrete_dtype

 | @property
 | discrete_dtype() -> np.dtype

The dtype of a discrete action.

ActionSpec Objects

class ActionSpec(NamedTuple)

A NamedTuple containing utility functions and information about the action spaces for a group of Agents under the same behavior.

  • num_continuous_actions is an int corresponding to the number of floats which constitute the action.
  • discrete_branch_sizes is a Tuple of int where each int corresponds to the number of discrete actions available to the agent on an independent action branch.

is_discrete

 | is_discrete() -> bool

Returns true if this Behavior uses discrete actions

is_continuous

 | is_continuous() -> bool

Returns true if this Behavior uses continuous actions

discrete_size

 | @property
 | discrete_size() -> int

Returns a an int corresponding to the number of discrete branches.

empty_action

 | empty_action(n_agents: int) -> ActionTuple

Generates ActionTuple corresponding to an empty action (all zeros) for a number of agents.

Arguments:

  • n_agents: The number of agents that will have actions generated

random_action

 | random_action(n_agents: int) -> ActionTuple

Generates ActionTuple corresponding to a random action (either discrete or continuous) for a number of agents.

Arguments:

  • n_agents: The number of agents that will have actions generated

create_continuous

 | @staticmethod
 | create_continuous(continuous_size: int) -> "ActionSpec"

Creates an ActionSpec that is homogenously continuous

create_discrete

 | @staticmethod
 | create_discrete(discrete_branches: Tuple[int]) -> "ActionSpec"

Creates an ActionSpec that is homogenously discrete

DimensionProperty Objects

class DimensionProperty(IntFlag)

No properties specified.

UNSPECIFIED

No Property of the observation in that dimension. Observation can be processed with Fully connected networks.

NONE

Means it is suitable to do a convolution in this dimension.

TRANSLATIONAL_EQUIVARIANCE

Means that there can be a variable number of observations in this dimension. The observations are unordered.

ObservationType Objects

class ObservationType(Enum)

An Enum which defines the type of information carried in the observation of the agent.

ObservationSpec Objects

class ObservationSpec(NamedTuple)

A NamedTuple containing information about the observation of Agents.

  • shape is a Tuple of int : It corresponds to the shape of an observation's dimensions.
  • dimension_property is a Tuple of DimensionProperties flag, one flag for each dimension.
  • observation_type is an enum of ObservationType.

BehaviorSpec Objects

class BehaviorSpec(NamedTuple)

A NamedTuple containing information about the observation and action spaces for a group of Agents under the same behavior.

  • observation_specs is a List of ObservationSpec NamedTuple containing information about the information of the Agent's observations such as their shapes. The order of the ObservationSpec is the same as the order of the observations of an agent.
  • action_spec is an ActionSpec NamedTuple.

BaseEnv Objects

class BaseEnv(ABC)

step

 | @abstractmethod
 | step() -> None

Signals the environment that it must move the simulation forward by one step.

reset

 | @abstractmethod
 | reset() -> None

Signals the environment that it must reset the simulation.

close

 | @abstractmethod
 | close() -> None

Signals the environment that it must close.

behavior_specs

 | @property
 | @abstractmethod
 | behavior_specs() -> MappingType[str, BehaviorSpec]

Returns a Mapping from behavior names to behavior specs. Agents grouped under the same behavior name have the same action and observation specs, and are expected to behave similarly in the environment. Note that new keys can be added to this mapping as new policies are instantiated.

set_actions

 | @abstractmethod
 | set_actions(behavior_name: BehaviorName, action: ActionTuple) -> None

Sets the action for all of the agents in the simulation for the next step. The Actions must be in the same order as the order received in the DecisionSteps.

Arguments:

  • behavior_name: The name of the behavior the agents are part of
  • action: ActionTuple tuple of continuous and/or discrete action. Actions are np.arrays with dimensions (n_agents, continuous_size) and (n_agents, discrete_size), respectively.

set_action_for_agent

 | @abstractmethod
 | set_action_for_agent(behavior_name: BehaviorName, agent_id: AgentId, action: ActionTuple) -> None

Sets the action for one of the agents in the simulation for the next step.

Arguments:

  • behavior_name: The name of the behavior the agent is part of
  • agent_id: The id of the agent the action is set for
  • action: ActionTuple tuple of continuous and/or discrete action Actions are np.arrays with dimensions (1, continuous_size) and (1, discrete_size), respectively. Note, this initial dimensions of 1 is because this action is meant for a single agent.

get_steps

 | @abstractmethod
 | get_steps(behavior_name: BehaviorName) -> Tuple[DecisionSteps, TerminalSteps]

Retrieves the steps of the agents that requested a step in the simulation.

Arguments:

  • behavior_name: The name of the behavior the agents are part of

Returns:

A tuple containing :

  • A DecisionSteps NamedTuple containing the observations, the rewards, the agent ids and the action masks for the Agents of the specified behavior. These Agents need an action this step.
  • A TerminalSteps NamedTuple containing the observations, rewards, agent ids and interrupted flags of the agents that had their episode terminated last step.

mlagents_envs.communicator

Communicator Objects

class Communicator()

__init__

 | __init__(worker_id=0, base_port=5005)

Python side of the communication. Must be used in pair with the right Unity Communicator equivalent.

:int worker_id: Offset from base_port. Used for training multiple environments simultaneously. :int base_port: Baseline port number to connect to Unity environment over. worker_id increments over this.

initialize

 | initialize(inputs: UnityInputProto, poll_callback: Optional[PollCallback] = None) -> UnityOutputProto

Used to exchange initialization parameters between Python and the Environment

Arguments:

  • inputs: The initialization input that will be sent to the environment.
  • poll_callback: Optional callback to be used while polling the connection.

Returns:

UnityOutput: The initialization output sent by Unity

exchange

 | exchange(inputs: UnityInputProto, poll_callback: Optional[PollCallback] = None) -> Optional[UnityOutputProto]

Used to send an input and receive an output from the Environment

Arguments:

  • inputs: The UnityInput that needs to be sent the Environment
  • poll_callback: Optional callback to be used while polling the connection.

Returns:

The UnityOutputs generated by the Environment

close

 | close()

Sends a shutdown signal to the unity environment, and closes the connection.

mlagents_envs.environment

UnityEnvironment Objects

class UnityEnvironment(BaseEnv)

__init__

 | __init__(file_name: Optional[str] = None, worker_id: int = 0, base_port: Optional[int] = None, seed: int = 0, no_graphics: bool = False, timeout_wait: int = 60, additional_args: Optional[List[str]] = None, side_channels: Optional[List[SideChannel]] = None, log_folder: Optional[str] = None)

Starts a new unity environment and establishes a connection with the environment. Notice: Currently communication between Unity and Python takes place over an open socket without authentication. Ensure that the network where training takes place is secure.

:string file_name: Name of Unity environment binary. :int base_port: Baseline port number to connect to Unity environment over. worker_id increments over this. If no environment is specified (i.e. file_name is None), the DEFAULT_EDITOR_PORT will be used. :int worker_id: Offset from base_port. Used for training multiple environments simultaneously. :bool no_graphics: Whether to run the Unity simulator in no-graphics mode :int timeout_wait: Time (in seconds) to wait for connection from environment. :list args: Addition Unity command line arguments :list side_channels: Additional side channel for no-rl communication with Unity :str log_folder: Optional folder to write the Unity Player log file into. Requires absolute path.

close

 | close()

Sends a shutdown signal to the unity environment, and closes the socket connection.

mlagents_envs.registry

mlagents_envs.registry.unity_env_registry

UnityEnvRegistry Objects

class UnityEnvRegistry(Mapping)

UnityEnvRegistry

Provides a library of Unity environments that can be launched without the need of downloading the Unity Editor. The UnityEnvRegistry implements a Map, to access an entry of the Registry, use:

registry = UnityEnvRegistry()
entry = registry[<environment_identifyier>]

An entry has the following properties :

  • identifier : Uniquely identifies this environment
  • expected_reward : Corresponds to the reward an agent must obtained for the task to be considered completed.
  • description : A human readable description of the environment.

To launch a Unity environment from a registry entry, use the make method:

registry = UnityEnvRegistry()
env = registry[<environment_identifyier>].make()

register

 | register(new_entry: BaseRegistryEntry) -> None

Registers a new BaseRegistryEntry to the registry. The BaseRegistryEntry.identifier value will be used as indexing key. If two are more environments are registered under the same key, the most recentry added will replace the others.

register_from_yaml

 | register_from_yaml(path_to_yaml: str) -> None

Registers the environments listed in a yaml file (either local or remote). Note that the entries are registered lazily: the registration will only happen when an environment is accessed. The yaml file must have the following format :

environments:
- <identifier of the first environment>:
    expected_reward: <expected reward of the environment>
    description: | <a multi line description of the environment>
      <continued multi line description>
    linux_url: <The url for the Linux executable zip file>
    darwin_url: <The url for the OSX executable zip file>
    win_url: <The url for the Windows executable zip file>

- <identifier of the second environment>:
    expected_reward: <expected reward of the environment>
    description: | <a multi line description of the environment>
      <continued multi line description>
    linux_url: <The url for the Linux executable zip file>
    darwin_url: <The url for the OSX executable zip file>
    win_url: <The url for the Windows executable zip file>

- ...

Arguments:

  • path_to_yaml: A local path or url to the yaml file

clear

 | clear() -> None

Deletes all entries in the registry.

__getitem__

 | __getitem__(identifier: str) -> BaseRegistryEntry

Returns the BaseRegistryEntry with the provided identifier. BaseRegistryEntry can then be used to make a Unity Environment.

Arguments:

  • identifier: The identifier of the BaseRegistryEntry

Returns:

The associated BaseRegistryEntry

mlagents_envs.registry.binary_utils

get_local_binary_path

get_local_binary_path(name: str, url: str) -> str

Returns the path to the executable previously downloaded with the name argument. If None is found, the executable at the url argument will be downloaded and stored under name for future uses.

Arguments:

  • name: The name that will be given to the folder containing the extracted data
  • url: The URL of the zip file

get_local_binary_path_if_exists

get_local_binary_path_if_exists(name: str, url: str) -> Optional[str]

Recursively searches for a Unity executable in the extracted files folders. This is platform dependent : It will only return a Unity executable compatible with the computer's OS. If no executable is found, None will be returned.

Arguments:

  • name: The name/identifier of the executable
  • url: The url the executable was downloaded from (for verification)

get_tmp_dir

get_tmp_dir() -> Tuple[str, str]

Returns the path to the folder containing the downloaded zip files and the extracted binaries. If these folders do not exist, they will be created. :retrun: Tuple containing path to : (zip folder, extracted files folder)

download_and_extract_zip

download_and_extract_zip(url: str, name: str) -> None

Downloads a zip file under a URL, extracts its contents into a folder with the name argument and gives chmod 755 to all the files it contains. Files are downloaded and extracted into special folders in the temp folder of the machine.

Arguments:

  • url: The URL of the zip file
  • name: The name that will be given to the folder containing the extracted data

print_progress

print_progress(prefix: str, percent: float) -> None

Displays a single progress bar in the terminal with value percent.

Arguments:

  • prefix: The string that will precede the progress bar.
  • percent: The percent progression of the bar (min is 0, max is 100)

load_remote_manifest

load_remote_manifest(url: str) -> Dict[str, Any]

Converts a remote yaml file into a Python dictionary

load_local_manifest

load_local_manifest(path: str) -> Dict[str, Any]

Converts a local yaml file into a Python dictionary

ZipFileWithProgress Objects

class ZipFileWithProgress(ZipFile)

This is a helper class inheriting from ZipFile that allows to display a progress bar while the files are being extracted.

mlagents_envs.registry.remote_registry_entry

RemoteRegistryEntry Objects

class RemoteRegistryEntry(BaseRegistryEntry)

__init__

 | __init__(identifier: str, expected_reward: Optional[float], description: Optional[str], linux_url: Optional[str], darwin_url: Optional[str], win_url: Optional[str], additional_args: Optional[List[str]] = None)

A RemoteRegistryEntry is an implementation of BaseRegistryEntry that uses a Unity executable downloaded from the internet to launch a UnityEnvironment. Note: The url provided must be a link to a .zip file containing a single compressed folder with the executable inside. There can only be one executable in the folder and it must be at the root of the folder.

Arguments:

  • identifier: The name of the Unity Environment.
  • expected_reward: The cumulative reward that an Agent must receive for the task to be considered solved.
  • description: A description of the Unity Environment. Contains human readable information about potential special arguments that the make method can take as well as information regarding the observation, reward, actions, behaviors and number of agents in the Environment.
  • linux_url: The url of the Unity executable for the Linux platform
  • darwin_url: The url of the Unity executable for the OSX platform
  • win_url: The url of the Unity executable for the Windows platform

make

 | make(**kwargs: Any) -> BaseEnv

Returns the UnityEnvironment that corresponds to the Unity executable found at the provided url. The arguments passed to this method will be passed to the constructor of the UnityEnvironment (except for the file_name argument)

mlagents_envs.registry.base_registry_entry

BaseRegistryEntry Objects

class BaseRegistryEntry()

__init__

 | __init__(identifier: str, expected_reward: Optional[float], description: Optional[str])

BaseRegistryEntry allows launching a Unity Environment with its make method.

Arguments:

  • identifier: The name of the Unity Environment.
  • expected_reward: The cumulative reward that an Agent must receive for the task to be considered solved.
  • description: A description of the Unity Environment. Contains human readable information about potential special arguments that the make method can take as well as information regarding the observation, reward, actions, behaviors and number of agents in the Environment.

identifier

 | @property
 | identifier() -> str

The unique identifier of the entry

expected_reward

 | @property
 | expected_reward() -> Optional[float]

The cumulative reward that an Agent must receive for the task to be considered solved.

description

 | @property
 | description() -> Optional[str]

A description of the Unity Environment the entry can make.

make

 | @abstractmethod
 | make(**kwargs: Any) -> BaseEnv

This method creates a Unity BaseEnv (usually a UnityEnvironment).

mlagents_envs.side_channel

mlagents_envs.side_channel.raw_bytes_channel

RawBytesChannel Objects

class RawBytesChannel(SideChannel)

This is an example of what the SideChannel for raw bytes exchange would look like. Is meant to be used for general research purpose.

on_message_received

 | on_message_received(msg: IncomingMessage) -> None

Is called by the environment to the side channel. Can be called multiple times per step if multiple messages are meant for that SideChannel.

get_and_clear_received_messages

 | get_and_clear_received_messages() -> List[bytes]

returns a list of bytearray received from the environment.

send_raw_data

 | send_raw_data(data: bytearray) -> None

Queues a message to be sent by the environment at the next call to step.

mlagents_envs.side_channel.outgoing_message

OutgoingMessage Objects

class OutgoingMessage()

Utility class for forming the message that is written to a SideChannel. All data is written in little-endian format using the struct module.

__init__

 | __init__()

Create an OutgoingMessage with an empty buffer.

write_bool

 | write_bool(b: bool) -> None

Append a boolean value.

write_int32

 | write_int32(i: int) -> None

Append an integer value.

write_float32

 | write_float32(f: float) -> None

Append a float value. It will be truncated to 32-bit precision.

write_float32_list

 | write_float32_list(float_list: List[float]) -> None

Append a list of float values. They will be truncated to 32-bit precision.

write_string

 | write_string(s: str) -> None

Append a string value. Internally, it will be encoded to ascii, and the encoded length will also be written to the message.

set_raw_bytes

 | set_raw_bytes(buffer: bytearray) -> None

Set the internal buffer to a new bytearray. This will overwrite any existing data.

Arguments:

  • buffer:

Returns:

mlagents_envs.side_channel.engine_configuration_channel

EngineConfigurationChannel Objects

class EngineConfigurationChannel(SideChannel)

This is the SideChannel for engine configuration exchange. The data in the engine configuration is as follows :

  • int width;
  • int height;
  • int qualityLevel;
  • float timeScale;
  • int targetFrameRate;
  • int captureFrameRate;

on_message_received

 | on_message_received(msg: IncomingMessage) -> None

Is called by the environment to the side channel. Can be called multiple times per step if multiple messages are meant for that SideChannel. Note that Python should never receive an engine configuration from Unity

set_configuration_parameters

 | set_configuration_parameters(width: Optional[int] = None, height: Optional[int] = None, quality_level: Optional[int] = None, time_scale: Optional[float] = None, target_frame_rate: Optional[int] = None, capture_frame_rate: Optional[int] = None) -> None

Sets the engine configuration. Takes as input the configurations of the engine.

Arguments:

  • width: Defines the width of the display. (Must be set alongside height)
  • height: Defines the height of the display. (Must be set alongside width)
  • quality_level: Defines the quality level of the simulation.
  • time_scale: Defines the multiplier for the deltatime in the simulation. If set to a higher value, time will pass faster in the simulation but the physics might break.
  • target_frame_rate: Instructs simulation to try to render at a specified frame rate.
  • capture_frame_rate: Instructs the simulation to consider time between updates to always be constant, regardless of the actual frame rate.

set_configuration

 | set_configuration(config: EngineConfig) -> None

Sets the engine configuration. Takes as input an EngineConfig.

mlagents_envs.side_channel.side_channel_manager

SideChannelManager Objects

class SideChannelManager()

process_side_channel_message

 | process_side_channel_message(data: bytes) -> None

Separates the data received from Python into individual messages for each registered side channel and calls on_message_received on them.

Arguments:

  • data: The packed message sent by Unity

generate_side_channel_messages

 | generate_side_channel_messages() -> bytearray

Gathers the messages that the registered side channels will send to Unity and combines them into a single message ready to be sent.

mlagents_envs.side_channel.stats_side_channel

StatsSideChannel Objects

class StatsSideChannel(SideChannel)

Side channel that receives (string, float) pairs from the environment, so that they can eventually be passed to a StatsReporter.

on_message_received

 | on_message_received(msg: IncomingMessage) -> None

Receive the message from the environment, and save it for later retrieval.

Arguments:

  • msg:

Returns:

get_and_reset_stats

 | get_and_reset_stats() -> EnvironmentStats

Returns the current stats, and resets the internal storage of the stats.

Returns:

mlagents_envs.side_channel.incoming_message

IncomingMessage Objects

class IncomingMessage()

Utility class for reading the message written to a SideChannel. Values must be read in the order they were written.

__init__

 | __init__(buffer: bytes, offset: int = 0)

Create a new IncomingMessage from the bytes.

read_bool

 | read_bool(default_value: bool = False) -> bool

Read a boolean value from the message buffer.

Arguments:

  • default_value: Default value to use if the end of the message is reached.

Returns:

The value read from the message, or the default value if the end was reached.

read_int32

 | read_int32(default_value: int = 0) -> int

Read an integer value from the message buffer.

Arguments:

  • default_value: Default value to use if the end of the message is reached.

Returns:

The value read from the message, or the default value if the end was reached.

read_float32

 | read_float32(default_value: float = 0.0) -> float

Read a float value from the message buffer.

Arguments:

  • default_value: Default value to use if the end of the message is reached.

Returns:

The value read from the message, or the default value if the end was reached.

read_float32_list

 | read_float32_list(default_value: List[float] = None) -> List[float]

Read a list of float values from the message buffer.

Arguments:

  • default_value: Default value to use if the end of the message is reached.

Returns:

The value read from the message, or the default value if the end was reached.

read_string

 | read_string(default_value: str = "") -> str

Read a string value from the message buffer.

Arguments:

  • default_value: Default value to use if the end of the message is reached.

Returns:

The value read from the message, or the default value if the end was reached.

get_raw_bytes

 | get_raw_bytes() -> bytes

Get a copy of the internal bytes used by the message.

mlagents_envs.side_channel.float_properties_channel

FloatPropertiesChannel Objects

class FloatPropertiesChannel(SideChannel)

This is the SideChannel for float properties shared with Unity. You can modify the float properties of an environment with the commands set_property, get_property and list_properties.

on_message_received

 | on_message_received(msg: IncomingMessage) -> None

Is called by the environment to the side channel. Can be called multiple times per step if multiple messages are meant for that SideChannel.

set_property

 | set_property(key: str, value: float) -> None

Sets a property in the Unity Environment.

Arguments:

  • key: The string identifier of the property.
  • value: The float value of the property.

get_property

 | get_property(key: str) -> Optional[float]

Gets a property in the Unity Environment. If the property was not found, will return None.

Arguments:

  • key: The string identifier of the property.

Returns:

The float value of the property or None.

list_properties

 | list_properties() -> List[str]

Returns a list of all the string identifiers of the properties currently present in the Unity Environment.

get_property_dict_copy

 | get_property_dict_copy() -> Dict[str, float]

Returns a copy of the float properties.

Returns:

mlagents_envs.side_channel.environment_parameters_channel

EnvironmentParametersChannel Objects

class EnvironmentParametersChannel(SideChannel)

This is the SideChannel for sending environment parameters to Unity. You can send parameters to an environment with the command set_float_parameter.

set_float_parameter

 | set_float_parameter(key: str, value: float) -> None

Sets a float environment parameter in the Unity Environment.

Arguments:

  • key: The string identifier of the parameter.
  • value: The float value of the parameter.

set_uniform_sampler_parameters

 | set_uniform_sampler_parameters(key: str, min_value: float, max_value: float, seed: int) -> None

Sets a uniform environment parameter sampler.

Arguments:

  • key: The string identifier of the parameter.
  • min_value: The minimum of the sampling distribution.
  • max_value: The maximum of the sampling distribution.
  • seed: The random seed to initialize the sampler.

set_gaussian_sampler_parameters

 | set_gaussian_sampler_parameters(key: str, mean: float, st_dev: float, seed: int) -> None

Sets a gaussian environment parameter sampler.

Arguments:

  • key: The string identifier of the parameter.
  • mean: The mean of the sampling distribution.
  • st_dev: The standard deviation of the sampling distribution.
  • seed: The random seed to initialize the sampler.

set_multirangeuniform_sampler_parameters

 | set_multirangeuniform_sampler_parameters(key: str, intervals: List[Tuple[float, float]], seed: int) -> None

Sets a multirangeuniform environment parameter sampler.

Arguments:

  • key: The string identifier of the parameter.
  • intervals: The lists of min and max that define each uniform distribution.
  • seed: The random seed to initialize the sampler.

mlagents_envs.side_channel.side_channel

SideChannel Objects

class SideChannel(ABC)

The side channel just get access to a bytes buffer that will be shared between C# and Python. For example, We will create a specific side channel for properties that will be a list of string (fixed size) to float number, that can be modified by both C# and Python. All side channels are passed to the Env object at construction.

queue_message_to_send

 | queue_message_to_send(msg: OutgoingMessage) -> None

Queues a message to be sent by the environment at the next call to step.

on_message_received

 | @abstractmethod
 | on_message_received(msg: IncomingMessage) -> None

Is called by the environment to the side channel. Can be called multiple times per step if multiple messages are meant for that SideChannel.

channel_id

 | @property
 | channel_id() -> uuid.UUID

Returns:

The type of side channel used. Will influence how the data is processed in the environment.