Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch issues and pull requests
#89 - Bump torch from 0.4.1.post2 to 2.2.0
Pull Request -
State: open - Opened by dependabot[bot] about 2 months ago
Labels: dependencies
#88 - [Question] How was the target entropy in the discrete SAC chosen?
Issue -
State: open - Opened by aivarsoo 8 months ago
#87 - puzzle about envs
Issue -
State: open - Opened by GongYanfu 9 months ago
#86 - Safe Interruptibility training
Pull Request -
State: closed - Opened by PallottaEnrico over 1 year ago
#85 - A question about critic-loss in discrete sac?
Issue -
State: open - Opened by outshine-J almost 2 years ago
- 5 comments
#84 - YYT-test
Pull Request -
State: closed - Opened by levanaLYF about 2 years ago
- 1 comment
#83 - Bump numpy from 1.15.2 to 1.22.0
Pull Request -
State: open - Opened by dependabot[bot] over 2 years ago
- 1 comment
Labels: dependencies
#82 - A question about DQN_With_Fixed_Q_Targets.
Issue -
State: open - Opened by LLYYKK over 2 years ago
#81 - KeyError: 'exploration_worker_difference'
Issue -
State: open - Opened by HHY1123 over 2 years ago
#80 - torch版本问题
Issue -
State: open - Opened by noc-turne over 2 years ago
- 4 comments
#79 - Question on SAC implementation
Issue -
State: open - Opened by fokx almost 3 years ago
#78 - ConnectionResetError: [Errno 104] Connection reset by peer
Issue -
State: open - Opened by JinQiangWang2021 almost 3 years ago
- 2 comments
#77 - terminate called after throwing an instance of 'at::Error' what(): CUDA error (3): initialization error (check_status at /pytorch/aten/src/ATen/cuda/detail/CUDAHooks.cpp:36)
Issue -
State: open - Opened by JinQiangWang2021 almost 3 years ago
- 3 comments
#76 - multi-dimensional action space?
Issue -
State: open - Opened by zhouwy-lv almost 3 years ago
#75 - SAC Discrete needs it's own `calculate_entropy_tuning_losses` function?
Issue -
State: closed - Opened by Harimus almost 3 years ago
#74 - Is there any error in discriminator loss in GAIL?
Issue -
State: open - Opened by Joywanglulu about 3 years ago
#73 - README link error
Issue -
State: open - Opened by JacobHA about 3 years ago
#72 - Code lines missing in Mountain_Car.py
Issue -
State: open - Opened by saketadhau over 3 years ago
#71 - Seeding in 'reset_game'
Issue -
State: open - Opened by Markus28 over 3 years ago
- 1 comment
#70 - Action selection in Continuous Action Space
Issue -
State: closed - Opened by sramakrishnan247 over 3 years ago
#69 - Visualize agent
Issue -
State: closed - Opened by sramakrishnan247 over 3 years ago
- 1 comment
#68 - Wrong parameter order
Issue -
State: open - Opened by leolyg over 3 years ago
#67 - atari+sac_discrete, AttributeError: 'AtariEnv' object has no attribute 'reward_threshold'
Issue -
State: open - Opened by weiguowilliam over 3 years ago
#66 - RuntimeError: cuda runtime error (801) : operation not supported at ..\torch/csrc/generic/StorageSharing.cpp:247
Issue -
State: open - Opened by zhouwy-lv over 3 years ago
#65 - Calculate Entropy Tuning Loss in SAC/SAC Discrete
Issue -
State: closed - Opened by xingdi-eric-yuan over 3 years ago
- 3 comments
#64 - Instructions require python 3.5-3.7
Issue -
State: open - Opened by gth828r over 3 years ago
#63 - Create LICENSE
Pull Request -
State: closed - Opened by p-christ over 3 years ago
#62 - For SAC-discrete version, is it possible to update model with input of state and action just like Sac-continuous version?
Issue -
State: open - Opened by dbsxdbsx almost 4 years ago
#61 - Wrong temperature loss implementation for discrete SAC
Issue -
State: closed - Opened by qiyan98 almost 4 years ago
- 2 comments
#60 - Bug fix for SAC-discrete.
Pull Request -
State: closed - Opened by toshikwa about 4 years ago
- 3 comments
#59 - Overlap between first evaluation episode and "min_steps_before_learning" in SAC
Issue -
State: open - Opened by pvdsp about 4 years ago
#58 - question on SAC for discrete action with temperature loss "alpha"
Issue -
State: closed - Opened by dbsxdbsx about 4 years ago
- 1 comment
#57 - fixed an error with using cpu
Pull Request -
State: closed - Opened by half-empty about 4 years ago
#56 - Sac Discrete Error
Issue -
State: closed - Opened by sshillo over 4 years ago
- 4 comments
#55 - max_probability_action bugfix for batchsize > 1
Pull Request -
State: closed - Opened by strombom over 4 years ago
#54 - Mean of expectation in SAC_discrete.py possibly wrong?
Issue -
State: closed - Opened by NikEyX over 4 years ago
- 11 comments
#53 - Weight Initialization for SAC Discrete
Issue -
State: open - Opened by nageshky97s over 4 years ago
#52 - SpaceInvaders(SAC_Discrete) : Error
Issue -
State: open - Opened by FarhaParveen919 over 4 years ago
- 4 comments
#51 - Exception in CartPole with A2C: AttributeError: 'Process' object has no attribute 'kill'
Issue -
State: open - Opened by acriptis over 4 years ago
#50 - Change torch version
Pull Request -
State: open - Opened by tom-doerr over 4 years ago
#49 - Could not find a version that satisfies the requirement torch==0.4.1.post2
Issue -
State: open - Opened by tom-doerr over 4 years ago
#48 - Fix typo
Pull Request -
State: closed - Opened by tom-doerr over 4 years ago
#47 - Implement model saves
Issue -
State: open - Opened by LucCADORET over 4 years ago
- 2 comments
#46 - Merge pull request #1 from p-christ/master
Pull Request -
State: closed - Opened by shijinming over 4 years ago
#45 - FileNotFoundError: [Errno 2] No such file or directory
Issue -
State: open - Opened by shuferhoo over 4 years ago
- 2 comments
#44 - TypeError: can't pickle _thread.RLock objects
Issue -
State: open - Opened by shuferhoo over 4 years ago
- 2 comments
#43 - fix space.Discrete type error
Pull Request -
State: closed - Opened by shuferhoo over 4 years ago
#42 - Actor output the wrong size in CartPole using PPO
Issue -
State: closed - Opened by yaoxunji over 4 years ago
- 1 comment
#42 - Actor output the wrong size in CartPole using PPO
Issue -
State: closed - Opened by yaoxunji over 4 years ago
- 1 comment
#41 - strange results
Issue -
State: closed - Opened by m1996 over 4 years ago
#40 - Dqn problem
Issue -
State: closed - Opened by m1996 over 4 years ago
- 2 comments
#39 - suggestion
Issue -
State: closed - Opened by m1996 over 4 years ago
- 3 comments
#38 - DDPG on MountainCar
Issue -
State: open - Opened by gearsuccess over 4 years ago
- 2 comments
#37 - There is no implementation of a function update_next_state_reward_done_and_score in REINFORCE
Issue -
State: open - Opened by Jungmo over 4 years ago
- 1 comment
#36 - Some questions abot Dueling DQN
Issue -
State: open - Opened by Yang-Yefeng almost 5 years ago
- 1 comment
#35 - AttributeError: 'TimeLimit' object has no attribute 'get_score_to_win'
Issue -
State: closed - Opened by olixu almost 5 years ago
- 1 comment
#34 - Reproduce Discrete Soft Actor Critic in TF 2.0
Issue -
State: closed - Opened by junhuang-ifast almost 5 years ago
- 1 comment
#33 - DDPG: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_addmm
Issue -
State: closed - Opened by MeixinZhu almost 5 years ago
- 2 comments
#32 - Device problem for DDQN
Issue -
State: open - Opened by ierezell almost 5 years ago
#31 - RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #4 'mat1'
Issue -
State: open - Opened by Jeffrey28 almost 5 years ago
- 9 comments
#30 - Can't run Fetch_Reach.py
Issue -
State: closed - Opened by SieRaX almost 5 years ago
- 1 comment
#29 - how to visualize the enviroment
Issue -
State: open - Opened by weixiang-95 almost 5 years ago
- 3 comments
#28 - ModuleNotFoundError: No module named 'nn_builder'
Issue -
State: closed - Opened by BaiLiping almost 5 years ago
- 2 comments
#27 - Issue running h_DQN
Issue -
State: open - Opened by tranhoangkhuongvn almost 5 years ago
#26 - path
Pull Request -
State: closed - Opened by christofer-f about 5 years ago
- 1 comment
#25 - Additional `critic_target gather` in SAC_discrete.py
Issue -
State: closed - Opened by YunqiuXu about 5 years ago
- 1 comment
#24 - change code in SAC.py row 107
Issue -
State: closed - Opened by christofer-f about 5 years ago
- 1 comment
#23 - feat: add a way of resuming training
Issue -
State: open - Opened by pedrohbtp about 5 years ago
- 1 comment
#22 - Problems running the A3C algorithm
Issue -
State: closed - Opened by christofer-f about 5 years ago
- 2 comments
#21 - An question about the actor loss calculation in `SAC_Discrete.py`.
Issue -
State: closed - Opened by ChangyWen about 5 years ago
- 2 comments
#20 - fix bug where first episode using Epsilon_Greedy_Exploration is random
Pull Request -
State: closed - Opened by simonalford42 about 5 years ago
- 1 comment
#19 - python import path update
Pull Request -
State: closed - Opened by hou-yz about 5 years ago
- 1 comment
#18 - Updating setup info
Issue -
State: open - Opened by simonalford42 over 5 years ago
- 2 comments
#17 - Add Callback Integration
Issue -
State: open - Opened by josiahls over 5 years ago
#16 - Convert Repository into package
Pull Request -
State: closed - Opened by josiahls over 5 years ago
#15 - Cart_Pole.py fails when running cuda9.0 gpu
Issue -
State: open - Opened by crashmatt over 5 years ago
- 3 comments
#14 - Results.X.py missing correct import path for Trainer
Issue -
State: closed - Opened by crashmatt over 5 years ago
- 2 comments
#13 - Gym env port
Pull Request -
State: closed - Opened by p-christ over 5 years ago
#12 - Fetch-Reach Result not running
Issue -
State: closed - Opened by MishaLaskin over 5 years ago
- 2 comments
#11 - Newgraphs
Pull Request -
State: closed - Opened by p-christ over 5 years ago
#10 - add PPO-HER
Issue -
State: open - Opened by 1576012404 over 5 years ago
- 5 comments
#9 - DDPG Acting Deterministically
Issue -
State: open - Opened by JohnBurden over 5 years ago
- 1 comment
#8 - Getting Nan as reward in training in PPO
Issue -
State: open - Opened by JohnBurden over 5 years ago
- 2 comments
#7 - Write README for each folder
Issue -
State: closed - Opened by p-christ over 5 years ago
Labels: help wanted, good first issue
#6 - Write a test for each agent that checks that it can solve a simple game
Issue -
State: closed - Opened by p-christ over 5 years ago
Labels: help wanted, good first issue
#5 - Fix bugs of CUDA multiprocessing and tensor dtype issue.
Pull Request -
State: closed - Opened by Vargnatt over 5 years ago
- 1 comment
#4 - What do you mean "to watch them train"?
Issue -
State: closed - Opened by Huixxi over 5 years ago
- 2 comments
#3 - Replay buffer for PPO
Issue -
State: closed - Opened by oribarel over 5 years ago
- 3 comments
#2 - Add A3C algorithm
Issue -
State: open - Opened by p-christ over 5 years ago
#1 - Add A2C algorithm
Issue -
State: open - Opened by p-christ over 5 years ago
- 2 comments