RLzoo is a collection of most practical reinforcement learning algorithms, frameworks and applications. It is implemented with Tensorflow 2.0 and API of neural network layers in TensorLayer 2, to provide a hands-on fast-developing approach for reinforcement learning practices. It supports basic toy-tests like OpenAI Gym and DeepMind Control Suite with very simple configurations. Moreover, RLzoo supports large-scale distributed training framework for more realistic scenarios with Unity 3D, Mujoco, Bullet Physics, and robotic learning tasks with Vrep/Pyrep, etc.
Please note that this repository using RL algorithms with high-level API. So if you want to get familiar with each algorithm more quickly, please look at our RL tutorials where each algorithm is implemented individually in a more straightforward manner.
Currently the repository is still in development, and there may be some envrionments incompatible with our algorithms. If you find any problems or have any suggestions, feel free to contact with us!
- python 3.5
- tensorflow >= 2.0.0 or tensorflow-gpu >= 2.0.0a0
- tensorlayer >= 2.0.1
- tensorflow-probability
- tf-nightly-2.0-preview
pip install -r requirements.txt
python3 main.py --env=Pendulum-v0 --algorithm=td3 --train_episodes=600 --mode=train
python3 main.py --env=BipedalWalker-v2 --algorithm=a3c --train_episodes=600 --mode=train --number_workers=2
python3 main.py --env=CartPole-v0 --algorithm=ac --train_episodes=600 --mode=train
python3 main.py --env=FrozenLake-v0 --algorithm=dqn --train_episodes=6000 --mode=train
- If you meet the error
AttributeError: module 'tensorflow' has no attribute 'contrib'
when running the code after installing tensorflow-probability, try:pip install --upgrade tf-nightly-2.0-preview tfp-nightly