Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / ShangtongZhang/DeepRL issues and pull requests
#111 - SAC example?
Issue -
State: open - Opened by fansstan 4 months ago
#110 - replay buffer: why next state start index is n_steps after state start index?
Issue -
State: closed - Opened by TaciturnMute over 1 year ago
#109 - Double constraints for updating actor?
Issue -
State: open - Opened by KhoiDOO over 1 year ago
#108 - Does the DAC code apply to robotics environment?
Issue -
State: open - Opened by data-null123 almost 3 years ago
- 1 comment
#107 - config parameters
Issue -
State: open - Opened by JordanAsh over 3 years ago
#106 - Continuous Control Reward and State Normalization
Issue -
State: closed - Opened by xkianteb over 3 years ago
#105 - Passing info from Actor to Agent in Async implementation?
Issue -
State: open - Opened by Louis-Bagot over 3 years ago
#104 - How to obtain the policy(logits) rather than only the actions from self.actor.step()
Issue -
State: closed - Opened by fuxianh over 3 years ago
- 2 comments
#103 - fix a minor issue replay.py
Pull Request -
State: open - Opened by ainilaha almost 4 years ago
#102 - Question about QUOTA-discrete
Issue -
State: closed - Opened by zhaoyingnan179346 almost 4 years ago
- 4 comments
#101 - Question about DeepRL-QUOTA-discrete
Issue -
State: closed - Opened by zhaoyingnan179346 almost 4 years ago
#100 - Reference for the network design
Issue -
State: closed - Opened by tilmto almost 4 years ago
- 2 comments
#99 - Adding elements to the Transition namedtuple
Issue -
State: closed - Opened by Louis-Bagot almost 4 years ago
- 3 comments
#98 - Asynchronous DQN
Issue -
State: closed - Opened by Louis-Bagot almost 4 years ago
- 4 comments
#97 - dqn_pixel doesn't work under the multiprocess setting of "config.num_workers = 5"
Issue -
State: closed - Opened by momofive almost 4 years ago
- 1 comment
#96 - Bump tensorflow from 1.15.0 to 1.15.4
Pull Request -
State: closed - Opened by dependabot[bot] almost 4 years ago
- 1 comment
Labels: dependencies
#95 - How much rewards can we get using DQN to play atari games usually?
Issue -
State: closed - Opened by DeepDuke about 4 years ago
#94 - Add baselines to requirements.txt
Issue -
State: closed - Opened by psurya1994 about 4 years ago
- 1 comment
#93 - using target network to calculate last state value
Issue -
State: closed - Opened by backpropper about 4 years ago
- 4 comments
#92 - I want to get the experimental data used to plot, if you are willing to
Issue -
State: closed - Opened by THSWind about 4 years ago
- 2 comments
#91 - How to get averaged curve of PPO online performance on Mujoco?
Issue -
State: closed - Opened by KarlXing about 4 years ago
- 2 comments
#90 - no module named baselines
Issue -
State: closed - Opened by AprilXiaoyanLiu about 4 years ago
- 2 comments
#89 - How can I use this package in python 3.7?
Issue -
State: closed - Opened by jiang-yuan about 4 years ago
- 1 comment
#88 - N-step target not working
Issue -
State: open - Opened by ShangtongZhang about 4 years ago
- 3 comments
Labels: help wanted
#87 - Option Critic e-greedy option update question
Issue -
State: closed - Opened by spacegoing about 4 years ago
- 2 comments
#86 - Option Critic Q value update question
Issue -
State: closed - Opened by spacegoing about 4 years ago
- 6 comments
#85 - Prioritized experience replay issue
Issue -
State: closed - Opened by Rajawat23 about 4 years ago
- 1 comment
#84 - N-step target in the rainbow implementation
Issue -
State: closed - Opened by ShangtongZhang about 4 years ago
- 1 comment
Labels: help wanted
#83 - fix a bug in replay
Pull Request -
State: closed - Opened by mingfeisun about 4 years ago
- 1 comment
#82 - CUDA multiprocessing error
Issue -
State: closed - Opened by spacegoing over 4 years ago
- 7 comments
#81 - How to plot the result of OC?
Issue -
State: closed - Opened by RushToNeverLand over 4 years ago
- 1 comment
#80 - [Question] VecEnv implementation
Issue -
State: closed - Opened by bycn over 4 years ago
- 1 comment
#79 - Is there any method to install baselines:8e56dd?
Issue -
State: closed - Opened by RushToNeverLand over 4 years ago
- 1 comment
#78 - Training using AsyncReplay gets stuck after arounf 50k steps.
Issue -
State: closed - Opened by ayooshkathuria over 4 years ago
- 1 comment
#77 - LSTM for PPOC
Pull Request -
State: closed - Opened by spacegoing over 4 years ago
- 4 comments
#76 - Bump tensorflow from 1.12.0 to 1.15.2
Pull Request -
State: closed - Opened by dependabot[bot] over 4 years ago
- 1 comment
Labels: dependencies
#75 - Environments usage permission
Issue -
State: closed - Opened by lich14 over 4 years ago
- 2 comments
#74 - Can not find cheetah backward
Issue -
State: closed - Opened by lich14 over 4 years ago
- 1 comment
#73 - Option-Critic Beta Advantage Question
Issue -
State: closed - Opened by spacegoing over 4 years ago
- 6 comments
#72 - Bump tensorflow from 1.12.0 to 1.15.0
Pull Request -
State: closed - Opened by dependabot[bot] almost 5 years ago
- 1 comment
Labels: dependencies
#71 - Why use policy over option's q value (Q_Omega) for intra-option policy updates?
Issue -
State: closed - Opened by spacegoing almost 5 years ago
- 1 comment
#70 - Is there any docker container on docker hub
Issue -
State: closed - Opened by spacegoing almost 5 years ago
- 1 comment
#69 - Some questions about DAC
Issue -
State: closed - Opened by Sunkworld almost 5 years ago
- 2 comments
#68 - test code running give unexpected results
Issue -
State: closed - Opened by fuxianh almost 5 years ago
- 2 comments
#67 - Random seed is fixed across runs
Issue -
State: closed - Opened by rpinsler almost 5 years ago
- 2 comments
#66 - Running multiple environments
Issue -
State: closed - Opened by neale almost 5 years ago
- 4 comments
#65 - size mismatch error for Gym Toy text environments
Issue -
State: closed - Opened by RaviTej310 almost 5 years ago
- 1 comment
#64 - How to implement eval_step() in BaseAgent()
Issue -
State: closed - Opened by forhonourlx almost 5 years ago
- 1 comment
#63 - set_one_thread() in example.py
Issue -
State: closed - Opened by jyf588 about 5 years ago
- 6 comments
#62 - name 'random_seed(seed)' is not defined
Issue -
State: closed - Opened by yongqianxiao about 5 years ago
- 1 comment
#61 - Why "End of Asynchronous Methods"?
Issue -
State: closed - Opened by ThyrixYang over 5 years ago
- 7 comments
#60 - Running your code on the server will appear: Segmentation fault (core dumped)
Issue -
State: closed - Opened by Kchu over 5 years ago
- 4 comments
#59 - can't run last experiments in examples.py
Issue -
State: closed - Opened by mehdimashayekhi over 5 years ago
- 2 comments
#58 - does it allow to save and load optimizer information in A2CAgent pixel
Issue -
State: closed - Opened by fuxianh over 5 years ago
- 3 comments
#57 - What's the difference of the feature and the pixels?
Issue -
State: closed - Opened by Kchu over 5 years ago
- 4 comments
#56 - Runtimeerror: size mismatch
Issue -
State: closed - Opened by fuxianh over 5 years ago
- 2 comments
#55 - Rendering with DummyVecEnv
Issue -
State: closed - Opened by Marianoetchart over 5 years ago
- 2 comments
#54 - How to run the code?
Issue -
State: closed - Opened by OptimusPrimeCao over 5 years ago
- 1 comment
#53 - DQN taking too long to converge
Issue -
State: closed - Opened by angerhang over 5 years ago
- 2 comments
#52 - Does DeepRL support multiple gpus or nn.DataParallel()?
Issue -
State: closed - Opened by forhonourlx over 5 years ago
- 1 comment
#51 - Docker script running into an error
Issue -
State: closed - Opened by typicalTYLER over 5 years ago
- 2 comments
#50 - Performance tendency of game Breakout is not same as the plot you put on the homepage
Issue -
State: closed - Opened by deeplearnerJHB over 5 years ago
- 2 comments
#49 - Does DQN on Pong work?
Issue -
State: closed - Opened by aviralkumar2907 over 5 years ago
- 4 comments
#48 - simple question about the episode return curve in README
Issue -
State: closed - Opened by deeplearnerJHB over 5 years ago
- 4 comments
#47 - quantile_regression_dqn_cart_pole()
Issue -
State: closed - Opened by ghost almost 6 years ago
- 1 comment
#46 - Memory leak?
Issue -
State: closed - Opened by djsaunde almost 6 years ago
- 3 comments
#45 - Running examples.py
Issue -
State: closed - Opened by yngtodd almost 6 years ago
- 7 comments
#44 - Simple Question
Issue -
State: closed - Opened by Sungtae-Lee almost 6 years ago
- 1 comment
#43 - entropy term in continuous spaces?
Issue -
State: closed - Opened by TomLin almost 6 years ago
- 2 comments
#42 - Model io branch
Pull Request -
State: closed - Opened by var95 almost 6 years ago
- 1 comment
#41 - What does torch.cuda.is_available() by itself do?
Issue -
State: closed - Opened by kenfehling about 6 years ago
- 2 comments
#40 - No Monitor Files
Issue -
State: closed - Opened by shisi-cc about 6 years ago
- 1 comment
#39 - Testing for DQN
Issue -
State: closed - Opened by damnOblivious about 6 years ago
- 1 comment
#38 - Fix for sync actor
Pull Request -
State: closed - Opened by ashigirl96 about 6 years ago
- 1 comment
#37 - Error when running the code
Issue -
State: closed - Opened by dakshanand about 6 years ago
- 4 comments
#36 - Error in A2C_agent.py?
Issue -
State: closed - Opened by ZmeiGorynych over 6 years ago
- 1 comment
#35 - Use logits in CategoricalActorCriticNet
Pull Request -
State: closed - Opened by wassname over 6 years ago
- 1 comment
#34 - How can I build the gpu version docker
Issue -
State: closed - Opened by xfdywy over 6 years ago
- 1 comment
#33 - Adding TRPO
Issue -
State: closed - Opened by JACKHAHA363 over 6 years ago
- 3 comments
Labels: help wanted
#32 - Segmentation fault when importing on a headless server
Issue -
State: closed - Opened by wassname over 6 years ago
- 2 comments
#31 - Option-Critic doesn't seem to converge
Issue -
State: closed - Opened by flrndttrch over 6 years ago
- 6 comments
#30 - Q learning: epsilon-greedy during test phase
Issue -
State: closed - Opened by tesslerc over 6 years ago
- 1 comment
#29 - where to download dataset
Issue -
State: closed - Opened by szrlee over 6 years ago
- 2 comments
#28 - P3O_continuous stuck in a loop.
Issue -
State: closed - Opened by murtazarang over 6 years ago
- 1 comment
#27 - Just a quick question
Issue -
State: closed - Opened by hohoCode over 6 years ago
- 2 comments
#26 - Dueling DQN ,The expanded size of the tensor (2) must match the existing size (10) at non-singleton dimension 1
Issue -
State: closed - Opened by jixian79 over 6 years ago
- 1 comment
#25 - fix issue 17
Pull Request -
State: closed - Opened by Officium over 6 years ago
- 2 comments
#24 - fix dataset config, handle no log dir
Pull Request -
State: closed - Opened by nadavbh12 over 6 years ago
- 1 comment
#23 - load_state_dict for Normalizer, StaticNormalizer
Pull Request -
State: closed - Opened by wassname over 6 years ago
- 1 comment
#22 - load and save for SharedReplay
Pull Request -
State: closed - Opened by wassname over 6 years ago
- 1 comment
#21 - Two questions
Issue -
State: closed - Opened by PKU-YYang over 6 years ago
- 1 comment
#20 - issue in async_agent.py
Issue -
State: closed - Opened by PKU-YYang over 6 years ago
- 1 comment
#19 - Bug fix
Pull Request -
State: closed - Opened by ihciah over 6 years ago
- 1 comment
#18 - DQN performance on Breakout
Issue -
State: closed - Opened by yhcao6 over 6 years ago
- 3 comments
#17 - Atari_wrapper different state shape
Issue -
State: closed - Opened by xfdywy over 6 years ago
- 2 comments
#16 - Package the project
Pull Request -
State: closed - Opened by kentsommer almost 7 years ago
- 2 comments
#15 - can not start the dqn_pixel_atari agent
Issue -
State: closed - Opened by SinaDitzel almost 7 years ago
- 1 comment
#14 - Optimizer and traning frequency
Issue -
State: closed - Opened by xfdywy almost 7 years ago
- 8 comments
#13 - Are you speed up the env?
Issue -
State: closed - Opened by Ja1r0 almost 7 years ago
- 4 comments
#7 - Issues with upgrade to PyTorch v0.2
Issue -
State: closed - Opened by ShangtongZhang almost 7 years ago
- 1 comment
Labels: hint