13 KiB
Migrating
Migrating from ML-Agents toolkit v0.11.0
Important Changes
Steps to Migrate
- We fixed a bug in
RayPerception3d.Perceive()
that was causing theendOffset
to be used incorrectly. However this may produce different behavior from previous versions if you use a non-zerostartOffset
. To reproduce the old behavior, you should increase the the value ofendOffset
bystartOffset
. You can verify your raycasts are performing as expected in scene view using the debug rays.
Migrating from ML-Agents toolkit v0.10 to v0.11.0
Important Changes
- The definition of the gRPC service has changed.
- The online BC training feature has been removed.
- The BroadcastHub has been deprecated. If there is a training Python process, all LearningBrains in the scene will automatically be trained. If there is no Python process, inference will be used.
- The Brain ScriptableObjects have been deprecated. The Brain Parameters are now on the Agent and are referred to as Behavior Parameters. Make sure the Behavior Parameters is attached to the Agent GameObject.
- Several changes were made to the setup for visual observations (i.e. using Cameras or RenderTextures):
- Camera resolutions are no longer stored in the Brain Parameters.
- AgentParameters no longer stores lists of Cameras and RenderTextures
- To add visual observations to an Agent, you must now attach a CameraSensorComponent or RenderTextureComponent to the agent. The corresponding Camera or RenderTexture can be added to these in the editor, and the resolution and color/grayscale is configured on the component itself.
Steps to Migrate
- In order to be able to train, make sure both your ML-Agents Python package and UnitySDK code come from the v0.11 release. Training will not work, for example, if you update the ML-Agents Python package, and only update the API Version in UnitySDK.
- If your Agents used visual observations, you must add a CameraSensorComponent corresponding to each old Camera in the Agent's camera list (and similarly for RenderTextures).
- Since Brain ScriptableObjects have been removed, you will need to delete all the Brain ScriptableObjects from your
Assets
folder. Then, add aBehavior Parameters
component to eachAgent
GameObject. You will then need to complete the fields on the newBehavior Parameters
component with the BrainParameters of the old Brain.
Migrating from ML-Agents toolkit v0.9 to v0.10
Important Changes
- We have updated the C# code in our repository to be in line with Unity Coding Conventions. This has changed the name of some public facing classes and enums.
- The example environments have been updated. If you were using these environments to benchmark your training, please note that the resulting rewards may be slightly different in v0.10.
Steps to Migrate
UnitySDK/Assets/ML-Agents/Scripts/Communicator.cs
and its classCommunicator
have been renamed toUnitySDK/Assets/ML-Agents/Scripts/ICommunicator.cs
andICommunicator
respectively.- The
SpaceType
Enumsdiscrete
, andcontinuous
have been renamed toDiscrete
andContinuous
. - We have removed the
Done
call as well as the capacity to setMax Steps
on the Academy. Therefore an AcademyReset will never be triggered from C# (only from Python). If you want to reset the simulation after a fixed number of steps, or when an event in the simulation occurs, we recommend looking at our multi-agent example environments (such as BananaCollector). In our examples, groups of Agents can be reset through an "Area" that can reset groups of Agents. - The import for
mlagents.envs.UnityEnvironment
was removed. If you are using the Python API, changefrom mlagents.envs import UnityEnvironment
tofrom mlagents.envs.environment import UnityEnvironment
.
Migrating from ML-Agents toolkit v0.8 to v0.9
Important Changes
- We have changed the way reward signals (including Curiosity) are defined in the
trainer_config.yaml
. - When using multiple environments, every "step" is recorded in TensorBoard.
- The steps in the command line console corresponds to a single step of a single environment.
Previously, each step corresponded to one step for all environments (i.e.,
num_envs
steps).
Steps to Migrate
- If you were overriding any of these following parameters in your config file, remove them
from the top-level config and follow the steps below:
gamma
: Define a newextrinsic
reward signal and set it'sgamma
to your new gamma.use_curiosity
,curiosity_strength
,curiosity_enc_size
: Define acuriosity
reward signal and set itsstrength
tocuriosity_strength
, andencoding_size
tocuriosity_enc_size
. Give it the samegamma
as yourextrinsic
signal to mimic previous behavior. See Reward Signals for more information on defining reward signals.
- TensorBoards generated when running multiple environments in v0.8 are not comparable to those generated in
v0.9 in terms of step count. Multiply your v0.8 step count by
num_envs
for an approximate comparison. You may need to changemax_steps
in your config as appropriate as well.
Migrating from ML-Agents toolkit v0.7 to v0.8
Important Changes
- We have split the Python packages into two separate packages
ml-agents
andml-agents-envs
. --worker-id
option oflearn.py
has been removed, use--base-port
instead if you'd like to run multiple instances oflearn.py
.
Steps to Migrate
- If you are installing via PyPI, there is no change.
- If you intend to make modifications to
ml-agents
orml-agents-envs
please check the Installing for Development in the Installation documentation.
Migrating from ML-Agents toolkit v0.6 to v0.7
Important Changes
- We no longer support TFS and are now using the Unity Inference Engine
Steps to Migrate
- Make sure to remove the
ENABLE_TENSORFLOW
flag in your Unity Project settings
Migrating from ML-Agents toolkit v0.5 to v0.6
Important Changes
-
Brains are now Scriptable Objects instead of MonoBehaviors.
-
You can no longer modify the type of a Brain. If you want to switch between
PlayerBrain
andLearningBrain
for multiple agents, you will need to assign a new Brain to each agent separately. Note: You can pass the same Brain to multiple agents in a scene by leveraging Unity's prefab system or look for all the agents in a scene using the search bar of theHierarchy
window with the wordAgent
. -
We replaced the Internal and External Brain with Learning Brain. When you need to train a model, you need to drag it into the
Broadcast Hub
inside theAcademy
and check theControl
checkbox. -
We removed the
Broadcast
checkbox of the Brain, to use the broadcast functionality, you need to drag the Brain into theBroadcast Hub
. -
When training multiple Brains at the same time, each model is now stored into a separate model file rather than in the same file under different graph scopes.
-
The Learning Brain graph scope, placeholder names, output names and custom placeholders can no longer be modified.
Steps to Migrate
- To update a scene from v0.5 to v0.6, you must:
- Remove the
Brain
GameObjects in the scene. (Delete all of the Brain GameObjects under Academy in the scene.) - Create new
Brain
Scriptable Objects usingAssets -> Create -> ML-Agents
for each type of the Brain you plan to use, and put the created files under a folder called Brains within your project. - Edit their
Brain Parameters
to be the same as the parameters used in theBrain
GameObjects. - Agents have a
Brain
field in the Inspector, you need to drag the appropriate Brain ScriptableObject in it. - The Academy has a
Broadcast Hub
field in the inspector, which is list of brains used in the scene. To train or control your Brain from themlagents-learn
Python script, you need to drag the relevantLearningBrain
ScriptableObjects used in your scene into entries into this list.
- Remove the
Migrating from ML-Agents toolkit v0.4 to v0.5
Important
- The Unity project
unity-environment
has been renamedUnitySDK
. - The
python
folder has been renamed toml-agents
. It now contains two packages,mlagents.env
andmlagents.trainers
.mlagents.env
can be used to interact directly with a Unity environment, whilemlagents.trainers
contains the classes for training agents. - The supported Unity version has changed from
2017.1 or later
to2017.4 or later
. 2017.4 is an LTS (Long Term Support) version that helps us maintain good quality and support. Earlier versions of Unity might still work, but you may encounter an error listed here.
Unity API
- Discrete Actions now use branches. You can now specify concurrent discrete actions. You will need to update the Brain Parameters in the Brain Inspector in all your environments that use discrete actions. Refer to the discrete action documentation for more information.
Python API
-
In order to run a training session, you can now use the command
mlagents-learn
instead ofpython3 learn.py
after installing themlagents
packages. This change is documented here. For example, if we previously ranpython3 learn.py 3DBall --train
from the
python
subdirectory (which is changed toml-agents
subdirectory in v0.5), we now runmlagents-learn config/trainer_config.yaml --env=3DBall --train
from the root directory where we installed the ML-Agents Toolkit.
-
It is now required to specify the path to the yaml trainer configuration file when running
mlagents-learn
. For an example trainer configuration file, see trainer_config.yaml. An example of passing a trainer configuration tomlagents-learn
is shown above. -
The environment name is now passed through the
--env
option. -
Curriculum learning has been changed. Refer to the curriculum learning documentation for detailed information. In summary:
- Curriculum files for the same environment must now be placed into a folder. Each curriculum file should be named after the Brain whose curriculum it specifies.
min_lesson_length
now specifies the minimum number of episodes in a lesson and affects reward thresholding.- It is no longer necessary to specify the
Max Steps
of the Academy to use curriculum learning.
Migrating from ML-Agents toolkit v0.3 to v0.4
Unity API
using MLAgents;
needs to be added in all of the C# scripts that use ML-Agents.
Python API
- We've changed some of the Python packages dependencies in requirement.txt
file. Make sure to run
pip3 install -e .
within yourml-agents/python
folder to update your Python packages.
Migrating from ML-Agents toolkit v0.2 to v0.3
There are a large number of new features and improvements in the ML-Agents toolkit v0.3 which change both the training process and Unity API in ways which will cause incompatibilities with environments made using older versions. This page is designed to highlight those changes for users familiar with v0.1 or v0.2 in order to ensure a smooth transition.
Important
- The ML-Agents toolkit is no longer compatible with Python 2.
Python Training
- The training script
ppo.py
andPPO.ipynb
Python notebook have been replaced with a singlelearn.py
script as the launching point for training with ML-Agents. For more information on usinglearn.py
, see here. - Hyperparameters for training Brains are now stored in the
trainer_config.yaml
file. For more information on using this file, see here.
Unity API
- Modifications to an Agent's rewards must now be done using either
AddReward()
orSetReward()
. - Setting an Agent to done now requires the use of the
Done()
method. CollectStates()
has been replaced byCollectObservations()
, which now no longer returns a list of floats.- To collect observations, call
AddVectorObs()
withinCollectObservations()
. Note that you can callAddVectorObs()
with floats, integers, lists and arrays of floats, Vector3 and Quaternions. AgentStep()
has been replaced byAgentAction()
.WaitTime()
has been removed.- The
Frame Skip
field of the Academy is replaced by the Agent'sDecision Frequency
field, enabling the Agent to make decisions at different frequencies. - The names of the inputs in the Internal Brain have been changed. You must
replace
state
withvector_observation
andobservation
withvisual_observation
. In addition, you must remove theepsilon
placeholder.
Semantics
In order to more closely align with the terminology used in the Reinforcement Learning field, and to be more descriptive, we have changed the names of some of the concepts used in ML-Agents. The changes are highlighted in the table below.
Old - v0.2 and earlier | New - v0.3 and later |
---|---|
State | Vector Observation |
Observation | Visual Observation |
Action | Vector Action |
N/A | Text Observation |
N/A | Text Action |