sweetice/Deep-reinforcement-learning-with-pytorch
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
PythonMIT
Issues
- 0
program error in gridworld.py
#46 opened by Wei-yao-Cheng - 6
Bugs in PPO
#6 opened by moonblue333 - 1
wrong code in SAC
#43 opened by QinwenLuo - 1
Error while seeding!
#45 opened by CajetanRodrigues - 2
A problem in Chapter 5: DDPG
#17 opened by MoonieC - 3
Big bug in PPO2
#35 opened by Vinson-sheep - 1
One parameter is missing in DDPG Code
#32 opened by catchy666 - 3
- 3
SAC Bugs
#25 opened by ZiyiLiubird - 2
bug in reinforce with baseline
#37 opened by hlhang9527 - 1
Temperature factor missing in SAC !!!
#36 opened by Darkness-hy - 0
what is your training performance on mujoco?
#33 opened by xiaoyuanzh - 3
- 0
about the advantage values in PPO2
#30 opened by Hardlygo - 4
I dont think PPO pendulum is converging
#7 opened by Bigpig4396 - 0
question to author
#28 opened by FulChou - 0
Are there TRPO implementations?
#27 opened by ChenDRAG - 0
About updating.
#26 opened by Michi-123 - 0
Some of the code was copied from Morvan
#23 opened by xiaoxuh - 1
About SAC's version bug (gym 0.17.3)
#21 opened by CoderAT13 - 0
- 0
Problem about DDPG
#18 opened by yikeqingli - 0
a bug in DQN.py
#15 opened by karlhjm - 0
about TRPO
#12 opened by wangyy161 - 0
- 0
- 0
why tensorboardX's abscissa is not accurate?
#9 opened by xiaoxuh - 1
Possible issue with policy decay in TD3.
#8 opened by WillBrennan - 1
Char 05 DDPG missing exploration noise
#3 opened by tomas-gajarsky - 1
Char 05 DDPG: step index and episode index
#5 opened by xiangzz - 0
- 1