reinforcement-learning-kr pg_travel issues

reinforcement-learning-kr / pg_travel

Policy Gradient algorithms (REINFORCE, NPG, TRPO, PPO)

MIT License

368 stars 76 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

PPO Model RuntimeError

#22 luminous-123 opened 1 year ago
0
이 repo의 코드들은 기본적으로 cpu에서 돌게 되어 있나요?

#21 pixar0407 opened 2 years ago
0
error of running ppo

#20 xiaoyuanzh opened 2 years ago
0
action = get_action(mu, std)[0]?

#19 xiaoyuanzh opened 2 years ago
0
why log standard deviation is fixed to 0

#18 dlrudco opened 3 years ago
0
Frequency of saving stats

#17 Rowing0914 closed 4 years ago
0
When i install mujoco and import mujoco_py, I got a problem ....

#16 wonchul-kim opened 6 years ago
10
Quick question about environment normalization

#15 MoMe36 opened 6 years ago
1
add test environment code

#14 dnddnjs closed 5 years ago
0
For testing model

#13 rrbb014 closed 6 years ago
0
메모리 구조 개선을 통한 학습 속도 향상

#12 dnddnjs closed 6 years ago
0
save and load n, M, S in RunningStat Class

#11 pz1004 closed 6 years ago
0
save and load n, M, and S value in RunningStat class

#10 pz1004 closed 6 years ago
0
Pyramid 환경에서 에이전트 PPO로 학습시켜보기

#9 dnddnjs opened 6 years ago
0
경사가 있는 환경에서 에이전트 학습시키기

#8 dnddnjs opened 6 years ago
0
unity multi 폴더 내부의 main.py와 ppo.py에서 torch tensor로 인한 error 수정

#7 dnddnjs closed 6 years ago
0
multi_agent

#6 Hyeokreal closed 6 years ago
1
linux 용 environment 추가 & 자동으로 cuda tensor 붙이기

#5 dnddnjs closed 6 years ago
0
add tensorboardX

#4 dnddnjs closed 6 years ago
0
README와 코드 주석 추가

#3 dnddnjs opened 6 years ago
4
코드를 서버에서 돌리기 위해 여러가지 설정 추가

#2 dnddnjs opened 6 years ago
0
학습 속도와 성능 개선을 위해 A2C 스타일의 PPO 에이전트 만들기

#1 dnddnjs opened 6 years ago
1