quantumiracle/Popular-RL-Algorithms
PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..
Jupyter NotebookApache-2.0
Issues
- 0
Environment setting about python version
#81 opened by vickychen928 - 2
- 1
About RL+LSTM
#67 opened by 4359hhh - 6
Why does PPO every training result in the same reward chart? This puzzles me very much.
#48 opened by Alexzzdfjcn - 3
ValueError on SAC v2 LSTM
#34 opened by sarmientoj24 - 1
- 1
Error:ppo_gae_discrete.py
#45 opened by lucifer2859 - 1
NameError: name 'last_action' is not defined
#42 opened by Nick-Kou - 3
- 1
How do I adjust SAC if I have a continuous action space that is more than -1 and 1
#33 opened by sarmientoj24 - 3
RDPG runs on MDP domains?
#31 opened by hai-h-nguyen - 1
Missing folders
#30 opened by hai-h-nguyen - 1
- 1
Does sac_v2_lstm support Pendulum-v0?
#19 opened by zhaoguangyuan123 - 1
Variable length episodes
#20 opened by alanmackey - 2
- 1
Stochastic Action sample seems not right to me
#11 opened by BigWZhu - 1
Issue in test mode of 'sac_v2_gru.py'
#14 opened by hynkis - 1
- 1
Parameters copying
#2 opened by manuelsh