seungeunrho/minimalRL issues and pull requests

#63 - Wrong formula for calc-target in SAC?

Issue - State: open - Opened by BeFranke about 2 months ago

#62 - Training speed is very slow！！！

Issue - State: open - Opened by xuzhou666 8 months ago - 1 comment

#61 - Update for the latest library enviromnet

Pull Request - State: closed - Opened by Lukious over 1 year ago - 1 comment

#60 - fixes syntax

Pull Request - State: open - Opened by lazybuttrying over 1 year ago - 1 comment

#59 - TypeError: expected np.ndarray (got tuple)

Issue - State: open - Opened by InguChoi almost 2 years ago - 1 comment

#58 - Remove redundant while loop break in dqn.py

Pull Request - State: open - Opened by ginoperrotta almost 3 years ago

#57 - DQN why train iterate for 10 times

Issue - State: open - Opened by FeynmanDNA almost 3 years ago

#56 - MuZero minimal implementation

Issue - State: open - Opened by ipsec about 3 years ago

#55 - Implemented r2d2

Pull Request - State: open - Opened by jsrimr about 3 years ago

#54 - implemented ape-x

Pull Request - State: open - Opened by jsrimr about 3 years ago

#53 - Update dqn.py

Pull Request - State: closed - Opened by jsrimr about 3 years ago

#52 - Minimal way to save / replay trained model?

Issue - State: open - Opened by HanClinto about 3 years ago

#51 - Add minimal IMPALA？

Issue - State: closed - Opened by meadewaking over 3 years ago - 2 comments

#50 - Query about LSTM

Issue - State: open - Opened by npitsillos over 3 years ago

#49 - Add meta RL algorithms?

Issue - State: open - Opened by ghost over 3 years ago

#48 - Cartpole environment with Multidiscrete action space

Issue - State: open - Opened by mg64ve over 3 years ago

#47 - Cartpole environment with Multidiscrete action space

Issue - State: closed - Opened by mgazzin over 3 years ago - 3 comments

#46 - A naive question about updating parameters in DDPG.

Issue - State: open - Opened by HiddenBeginner over 3 years ago

#45 - ppo minibatch version

Pull Request - State: open - Opened by seolhokim over 3 years ago

#44 - improve continuous-ppo

Pull Request - State: open - Opened by seolhokim over 3 years ago

#43 - Remove unused import

Issue - State: closed - Opened by neal2018 over 3 years ago - 1 comment

#42 - cartpole ppo train , reward drop

Issue - State: open - Opened by SeungyounShin over 3 years ago - 1 comment

#41 - Detach the target

Pull Request - State: closed - Opened by jsrimr almost 4 years ago - 1 comment

#40 - Maybe a bug in SAC Implementation?

Issue - State: closed - Opened by arthur-x almost 4 years ago - 1 comment

#39 - Use pytorch-lightning for better readability and optimization

Issue - State: open - Opened by EmmanuelMess almost 4 years ago

#38 - Soft Actor Critic?

Issue - State: closed - Opened by EmmanuelMess almost 4 years ago - 1 comment

#37 - TD3: Twin Delayed DDPG

Issue - State: open - Opened by zcaicaros almost 4 years ago - 2 comments

#36 - PPO update mistake?

Issue - State: closed - Opened by zcaicaros almost 4 years ago - 1 comment

#35 - fix ddpg data type error

Pull Request - State: closed - Opened by seolhokim almost 4 years ago - 1 comment

#34 - RuntimeError while running DDPG.py

Issue - State: closed - Opened by rl-max almost 4 years ago - 2 comments

#33 - The ratio in ppo.py should be detach() ?

Issue - State: closed - Opened by dedekinds about 4 years ago - 5 comments

#32 - Missing done mask?

Issue - State: closed - Opened by Junyoungpark about 4 years ago - 3 comments

#31 - torch.gather in relevant to policy gradient

Issue - State: open - Opened by migom6 over 4 years ago

#30 - PPO has no entropy factor

Issue - State: open - Opened by CesMak over 4 years ago

#29 - Questions about A3C

Issue - State: closed - Opened by ghost over 4 years ago - 1 comment

#28 - Termination of a CartPole episode in REINFORCE.py

Issue - State: closed - Opened by ansari1375 over 4 years ago - 1 comment

#27 - fix : #26 the bug that was updated per step was fixed

Pull Request - State: closed - Opened by seolhokim almost 5 years ago

#26 - Problem of `train_net()` in REINFORCE algorithm.

Issue - State: closed - Opened by fuyw almost 5 years ago - 5 comments

#26 - Problem of `train_net()` in REINFORCE algorithm.

Issue - State: closed - Opened by fuyw almost 5 years ago - 5 comments

#25 - Sac test

Pull Request - State: closed - Opened by seolhokim almost 5 years ago - 1 comment

#24 - td3 test

Pull Request - State: closed - Opened by seolhokim almost 5 years ago - 1 comment

#23 - continuous-ppo

Pull Request - State: closed - Opened by seolhokim almost 5 years ago - 3 comments

#22 - ddpg unnecessary codes has been deleted

Pull Request - State: closed - Opened by seolhokim almost 5 years ago

#21 - ddpg minor bug

Pull Request - State: closed - Opened by seolhokim almost 5 years ago - 1 comment

#20 - continuous ppo test version

Pull Request - State: closed - Opened by seolhokim almost 5 years ago - 1 comment

#19 - Add SAC?

Issue - State: closed - Opened by banma12956 almost 5 years ago

#18 - TF2 implementation for Policy Gradient Reinforce

Issue - State: closed - Opened by dragen1860 about 5 years ago

#17 - LSTM + PPO value fitting

Issue - State: closed - Opened by hnshahao about 5 years ago - 1 comment

#16 - Fix indexing error in retrace operation of ACER

Pull Request - State: closed - Opened by wwiiiii about 5 years ago - 1 comment

#15 - Wrong gradient flow in bias correction term of ACER?

Issue - State: closed - Opened by wwiiiii about 5 years ago - 1 comment

#14 - docs(README): add links to source code; format

Pull Request - State: closed - Opened by jjangga0214 about 5 years ago - 1 comment

#13 - Add A2C

Pull Request - State: closed - Opened by rahulptel about 5 years ago

#12 - PPO Continuous Action Space

Issue - State: closed - Opened by raunakdoesdev about 5 years ago - 2 comments

#11 - Add new algorithms

Issue - State: open - Opened by rahulptel about 5 years ago - 7 comments

#10 - Fix improper asynchronous updates in A3C

Pull Request - State: closed - Opened by rahulptel about 5 years ago

#9 - Improper asynchronous update in a3c

Issue - State: closed - Opened by rahulptel about 5 years ago - 1 comment

#8 - Wrong td_target and test() call in a3c implementation

Issue - State: closed - Opened by rahulptel about 5 years ago - 1 comment

#7 - Typo of actor_critic.py?

Issue - State: closed - Opened by seungwonpark about 5 years ago - 1 comment

#6 - Please add 1 continuous env

Issue - State: closed - Opened by bionicles over 5 years ago - 2 comments

#5 - Update ppo.py

Pull Request - State: closed - Opened by jsrimr over 5 years ago - 1 comment

#4 - Remove ReplayBuffer class

Pull Request - State: closed - Opened by jwergieluk over 5 years ago - 2 comments

GitHub / seungeunrho/minimalRL issues and pull requests