jingweiz pytorch-rl issues

jingweiz / pytorch-rl

Deep Reinforcement Learning with pytorch & visdom

MIT License

798 stars 143 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

only py2.7?

#18 Precola opened 4 years ago
1
Fixes #16

#17 scottwedge opened 4 years ago
0
Typo "calss"

#16 scottwedge opened 4 years ago
0
pytorch-rl-master

#15 H0803 opened 5 years ago
0
gpu

#14 shanxia opened 6 years ago
1
Added opensim-rl environment, extended dqn agent for multi-dimensional action space, and a sample configuration and options to config an agent to learn in opensim-rl

#13 praveen-palanisamy opened 6 years ago
0
Revert "Added opensim-rl environment and a sample configuration and options for a continuous DQN agent to learn in that environment"

#12 jingweiz closed 7 years ago
0
Can this code reproduce the performance of the baseline?

#11 xfdywy closed 7 years ago
3
Added opensim-rl environment and a sample configuration and options for a continuous DQN agent to learn in that environment

#10 praveen-palanisamy closed 7 years ago
7
Recurrent DQN

#9 ghost closed 7 years ago
1
update readme for pytorch 0.1.12

#8 onlytailei closed 7 years ago
1
* change scipy.misc.resize to cv2.resize

#7 onlytailei closed 7 years ago
0
* add agent detection in gym env

#6 onlytailei closed 7 years ago
0
Set default config to discrete a3c and fix the pi_vb initialization

#5 onlytailei closed 7 years ago
0
check mujoco dependency only when enable_continuous=True

#4 jingweiz closed 7 years ago
4
Add continuous control support of A3C on Mujoco-py

#3 onlytailei closed 7 years ago
0
Add the support the a3c continuous control

#2 onlytailei closed 7 years ago
0
In python3, change xrange to range to remove python NameError

#1 tigerneil closed 7 years ago
1