12kobe / sac-continuous-pytorch

a clean and robust Pytorch implementation of SAC on continuous action space

SAC-Continuous-Pytorch

A clean and robust Pytorch implementation of Soft-Actor-Critic on continuous action space.

BipedalWalkerHardcore	LunarLanderContinuous

Other RL algorithms by Pytorch can be found here.

Dependencies

gymnasium==0.29.1
numpy==1.26.1
pytorch==2.1.0

python==3.11.5

How to use my code

Train from scratch

python main.py

where the default enviroment is 'Pendulum'.

Play with trained model

python main.py --EnvIdex 0 --render True --Loadmodel True --ModelIdex 10

which will render the 'Pendulum'.

Change Enviroment

If you want to train on different enviroments, just run

python main.py --EnvIdex 1

The --EnvIdex can be set to be 0~5, where

'--EnvIdex 0' for 'Pendulum-v1'  
'--EnvIdex 1' for 'LunarLanderContinuous-v2'  
'--EnvIdex 2' for 'Humanoid-v4'  
'--EnvIdex 3' for 'HalfCheetah-v4'  
'--EnvIdex 4' for 'BipedalWalker-v3'  
'--EnvIdex 5' for 'BipedalWalkerHardcore-v3' 

Note: if you want train on BipedalWalker, BipedalWalkerHardcore, or LunarLanderContinuous, you need to install box2d-py first. You can install box2d-py via:

pip install gymnasium[box2d]

if you want train on Humanoid or HalfCheetah, you need to install MuJoCo first. You can install MuJoCo via:

pip install mujoco
pip install gymnasium[mujoco]

Visualize the training curve

You can use the tensorboard to record anv visualize the training curve.

• Installation (please make sure PyTorch is installed already):

pip install tensorboard
pip install packaging

• Record (the training curves will be saved at '\runs'):

python main.py --write True

• Visualization:

tensorboard --logdir runs

Hyperparameter Setting

For more details of Hyperparameter Setting, please check 'main.py'

Reference

Soft Actor-Critic Algorithms and Applications

All Training Curves

All the experiments are trained with same hyperparameters (see main.py).