It is possible to record demonstrations of agent behavior from the Unity Editor, and save them as assets. These demonstrations contain information on the observations, actions, and rewards for a given agent during the recording session. They can be managed from the Editor, as well as used for training with Offline Behavioral Cloning (see below).
It is possible to record demonstrations of agent behavior from the Unity Editor,
and save them as assets. These demonstrations contain information on the
observations, actions, and rewards for a given agent during the recording session.
They can be managed from the Editor, as well as used for training with Offline
Behavioral Cloning (see below).
In order to record demonstrations from an agent, add the `Demonstration Recorder` component to a GameObject in the scene which contains an `Agent` component. Once added, it is possible to name the demonstration that will be recorded from the agent.
In order to record demonstrations from an agent, add the `Demonstration Recorder`
component to a GameObject in the scene which contains an `Agent` component.
Once added, it is possible to name the demonstration that will be recorded
from the agent.
<palign="center">
<imgsrc="images/demo_component.png"
When `Record` is checked, a demonstration will be created whenever the scene is played from the Editor. Depending on the complexity of the task, anywhere from a few minutes or a few hours of demonstration data may be necessary to be useful for imitation learning. When you have recorded enough data, end the Editor play session, and a `.demo` file will be created in the `Assets/Demonstrations` folder. This file contains the demonstrations. Clicking on the file will provide metadata about the demonstration in the inspector.
When `Record` is checked, a demonstration will be created whenever the scene
is played from the Editor. Depending on the complexity of the task, anywhere
from a few minutes or a few hours of demonstration data may be necessary to
be useful for imitation learning. When you have recorded enough data, end
the Editor play session, and a `.demo` file will be created in the
`Assets/Demonstrations` folder. This file contains the demonstrations.
Clicking on the file will provide metadata about the demonstration in the
inspector.
<palign="center">
<imgsrc="images/demo_inspector.png"
## Training with Behavioral Cloning
There are a variety of possible imitation learning algorithms which can be used,
the simplest one of them is Behavioral Cloning. It works by collecting demonstrations from a teacher, and then simply uses them to directly learn a policy, in the
same way the supervised learning for image classification or other traditional
Machine Learning tasks work.
There are a variety of possible imitation learning algorithms which can
be used, the simplest one of them is Behavioral Cloning. It works by collecting
demonstrations from a teacher, and then simply uses them to directly learn a
policy, in the same way the supervised learning for image classification
or other traditional Machine Learning tasks work.
With offline behavioral cloning, we can use demonstrations (`.demo` files) generated using the `Demonstration Recorder` as the dataset used to train a behavior.
With offline behavioral cloning, we can use demonstrations (`.demo` files)
generated using the `Demonstration Recorder` as the dataset used to train a behavior.
2. Record a set of demonstration using the `Demonstration Recorder` (see above). For illustrative purposes we will refer to this file as `AgentRecording.demo`.
3. Build the scene, assigning the agent a Learning Brain, and set the Brain to Control in the Broadcast Hub. For more information on Brains, see [here](Learning-Environment-Design-Brains.md).
2. Record a set of demonstration using the `Demonstration Recorder` (see above).
For illustrative purposes we will refer to this file as `AgentRecording.demo`.
3. Build the scene, assigning the agent a Learning Brain, and set the Brain to
Control in the Broadcast Hub. For more information on Brains, see
[here](Learning-Environment-Design-Brains.md).
5. Modify the `demo_path` parameter in the file to reference the path to the demonstration file recorded in step 2. In our case this is: `./UnitySDK/Assets/Demonstrations/AgentRecording.demo`
6. Launch `mlagent-learn`, providing `./config/offline_bc_config.yaml` as the config parameter, and include the `--run-id` and `--train` as usual. Provide your environment as the `--env` parameter if it has been compiled as standalone, or omit to train in the editor.
5. Modify the `demo_path` parameter in the file to reference the path to the
demonstration file recorded in step 2. In our case this is:
as the config parameter, and include the `--run-id` and `--train` as usual.
Provide your environment as the `--env` parameter if it has been compiled
as standalone, or omit to train in the editor.
This will use the demonstration file to train a neural network driven agent to directly imitate the actions provided in the demonstration. The environment will launch and be used for evaluating the agent's performance during training.
This will use the demonstration file to train a neural network driven agent
to directly imitate the actions provided in the demonstration. The environment
will launch and be used for evaluating the agent's performance during training.
It is also possible to provide demonstrations in realtime during training, without pre-recording a demonstration file. The steps to do this are as follows:
It is also possible to provide demonstrations in realtime during training,
without pre-recording a demonstration file. The steps to do this are as follows:
1. First create two Brains, one which will be the "Teacher," and the other which
will be the "Student." We will assume that the names of the Brain
3. The "Student" Brain must be a **Learning Brain**.
4. The Brain Parameters of both the "Teacher" and "Student" Brains must be
compatible with the agent.
5. Drag both the "Teacher" and "Student" Brain into the Academy's `Broadcast Hub`
5. Drag both the "Teacher" and "Student" Brain into the Academy's `Broadcast Hub`
4. Link the Brains to the desired Agents (one Agent as the teacher and at least
6. Link the Brains to the desired Agents (one Agent as the teacher and at least
5. In `config/online_bc_config.yaml`, add an entry for the "Student" Brain. Set
the `trainer` parameter of this entry to `imitation`, and the
7. In `config/online_bc_config.yaml`, add an entry for the "Student" Brain. Set
the `trainer` parameter of this entry to `online_bc`, and the
6. Launch the training process with `mlagents-learn config/online_bc_config.yaml
8. Launch the training process with `mlagents-learn config/online_bc_config.yaml
7. From the Unity window, control the Agent with the Teacher Brain by providing
9. From the Unity window, control the Agent with the Teacher Brain by providing
8. Watch as the Agent(s) with the student Brain attached begin to behave
10. Watch as the Agent(s) with the student Brain attached begin to behave
9. Once the Student Agents are exhibiting the desired behavior, end the training
11. Once the Student Agents are exhibiting the desired behavior, end the training
10. Move the resulting `*.bytes` file into the `TFModels` subdirectory of the
12. Move the resulting `*.bytes` file into the `TFModels` subdirectory of the
Assets folder (or a subdirectory within Assets of your choosing) , and use
GitHub
6 年前