Reinforcement Learning Algorithms (that is to say, how the Neural Networks are updated) stay the same no matter the application. This package is designed so that these algorithms are only programmed once and can be "plugged & played" into different environments.
Consult the repository wiki for a guide on how to use the package
If you want to utilise the GPU with Pytorch install CUDA first - https://developer.nvidia.com/cuda-toolkit
Install Pytorch following the instructions here - https://pytorch.org/get-started/locally/
git clone
the repository into your desired directory on your local machine
Run pip3 install -r requirements.txt
in the root directory of the package
To make the module globally accessible in your working environment run pip3 install --editable .
in the project root
This package serves as a library of specific RL algorithms and utility functions being used by the CARES RL team. For an example of how to use this package in your own envrionments see the example gym packages below that use these algorithms for training agents on a variety of simulated and real-world tasks.
We have created a standardised general purpose gym that wraps the most common simulated environments used in reinforcement learning into a single easy to use place: https://github.com/UoA-CARES/gymnasium_envrionments
This package contains wrappers for the following gym environments:
The standard Deep Mind Control suite: https://github.com/google-deepmind/dm_control
The standard OpenAI Gymnasium: https://github.com/Farama-Foundation/Gymnasium
Environment running Gameboy games utilising the pyboy wrapper: https://github.com/UoA-CARES/pyboy_environment
The gripper gym contains all the code for training our dexterous robotic manipulators: https://github.com/UoA-CARES/gripper_gym
The Autonmous F1Tenth package contains all the code for training our F1Tenth platforms to autonmously race: https://github.com/UoA-CARES/autonomous_f1tenth
CARES RL provides a number of useful utility functions and classes for generating consistent results across the team. These utilities should be utilised in the new envrionments we build to test our approaches.
The Record class allows data to be saved into a consistent format during training. This allows all data to be consistently formatted for plotting against each other for fair and consistent evaluation.
All data from a training run is saved into '~/cares_rl_logs'. A folder will be created for each training run named as 'seed/ALGORITHM-TASK-YY_MM_DD:HH:MM:SS', e.g. '10/TD3-HalfCheetah-v4-23_10_11_08:47:22'. This folder will contain the following directories and information saved during the training session:
ALGORITHM-TASK-YY_MM_DD:HH:MM:SS/
├─ SEED
| ├─ env_config.py
| ├─ alg_config.py
| ├─ train_config.py
| ├─ data
| | ├─ train.csv
| | ├─ eval.csv
| ├─ figures
| | ├─ eval.png
| | ├─ train.png
| ├─ models
| | ├─ model.pht
| | ├─ CHECKPOINT_N.pht
| | ├─ ...
| ├─ videos
| | ├─ STEP.mp4
| | ├─ ...
├─ SEED...
├─ ...
The plotting utility will plot the data contained in the training data based on the format created by the Record class. An example of how to plot the data from one or multiple training sessions together is shown below.
Plot the results of a single training instance
python3 plotter.py -s ~/cares_rl_logs -d ~/cares_rl_logs/ALGORITHM/ALGORITHM-TASK-YY_MM_DD:HH:MM:SS
Plot and compare the results of two or more training instances
python3 plotter.py -s ~/cares_rl_logs -d ~/cares_rl_logs/ALGORITHM_A/ALGORITHM_A-TASK-YY_MM_DD:HH:MM:SS ~/cares_rl_logs/ALGORITHM_B/ALGORITHM_B-TASK-YY_MM_DD:HH:MM:SS
Running 'python3 plotter.py -h' will provide details on the plotting parameters and control arguements.
python3 plotter.py -h
Provides baseline dataclasses for environment, training, and algorithm configurations to allow for consistent recording of training parameters.
Provides a means of loading enevironment, training, and algorithm configurations through command line or configuration files. Enables consistent tracking of parameters when running training on various algorithms.
A factory class for creating a baseline RL algorithm that has been implemented into the CARES RL package.
A factory class for creating a memory buffer that has been implemented into the CARES RL package.
cares_reinforcement_learning/
├─ algorithm/
├─ policy/
│ │ ├─ TD3.py
│ │ ├─ ...
│ ├─ value/
│ │ ├─ DQN.py
│ │ ├─ ...
├─ networks/
│ ├─ DQN/
│ │ ├─ network.py
│ ├─ TD3.py/
│ │ ├─ actor.py
│ │ ├─ critic.py
│ ├─ ...
├─ memory/
│ ├─ prioritised_replay_buffer.py
├─ util/
│ ├─ network_factory.py
│ ├─ ...
algorithm
: contains update mechanisms for neural networks as defined by the algorithm.
networks
: contains standard neural networks that can be used with each algortihm
memory
: contains the implementation of various memory buffers - e.g. Priotised Experience Replay
util
: contains common utility classes
Algorithm | Observation Space | Action Space | Paper Reference |
---|---|---|---|
DQN | Vector | Discrete | DQN Paper |
DoubleDQN | Vector | Discrete | DoubleDQN Paper |
DuelingDQN | Vector | Discrete | DuelingDQN Paper |
----------- | -------------------------- | ------------ | --------------- |
PPO | Vector | Continuous | PPO Paper |
DDPG | Vector | Continuous | DDPG Paper |
TD3 | Vector | Continuous | TD3 Paper |
SAC | Vector | Continuous | SAC Paper |
PERTD3 | Vector | Continuous | PERTD3 Paper |
PERSAC | Vector | Continuous | PERSAC Paper |
PALTD3 | Vector | Continuous | PALTD3 Paper |
LAPTD3 | Vector | Continuous | LAPTD3 Paper |
LAPSAC | Vector | Continuous | LAPSAC Paper |
LA3PTD3 | Vector | Continuous | LA3PTD3 Paper |
LA3PSAC | Vector | Continuous | LA3PSAC Paper |
MAPERTD3 | Vector | Continuous | MAPERTD3 Paper |
MAPERSAC | Vector | Continuous | MAPERSAC Paper |
RDTD3 | Vector | Continuous | WIP |
RDSAC | Vector | Continuous | WIP |
REDQ | Vector | Continuous | REDQ Paper |
TQC | Vector | Continuous | TQC Paper |
CTD4 | Vector | Continuous | CTD4 Paper |
----------- | -------------------------- | ------------ | --------------- |
NaSATD3 | Image | Continuous | In Submission |
TD3AE | Image | Continuous | TD3AE Paper |
SACAE | Image | Continuous | SACAE Paper |