p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch

Issues

• torch版本问题

  #80 opened 2 years ago by noc-turne
  4

• [Question] How was the target entropy in the discrete SAC chosen?

  #88 opened 5 months ago by aivarsoo
  0

• puzzle about envs

  #87 opened 6 months ago by GongYanfu
  0

• ConnectionResetError: [Errno 104] Connection reset by peer

  #78 opened 3 years ago by JinQiangWang2021
  2

• SpaceInvaders(SAC_Discrete) : Error

  #52 opened 4 years ago by FarhaParveen919
  4

• A question about critic-loss in discrete sac？

  #85 opened 2 years ago by outshine-J
  5

• A question about DQN_With_Fixed_Q_Targets.

  #82 opened 2 years ago by LLYYKK
  0

• Mean of expectation in SAC_discrete.py possibly wrong?

  #54 opened 4 years ago by NikEyX
  11

• KeyError: 'exploration_worker_difference'

  #81 opened 2 years ago by HHY1123
  0

• Implement model saves

  #47 opened 4 years ago by LucCADORET
  2

• 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)

  #77 opened 3 years ago by JinQiangWang2021
  3

• Question on SAC implementation

  #79 opened 3 years ago by fokx
  0

• multi-dimensional action space?

  #76 opened 3 years ago by zhouwy-lv
  0

• SAC Discrete needs it's own `calculate_entropy_tuning_losses` function?

  #75 opened 3 years ago by Harimus
  0

• Is there any error in discriminator loss in GAIL?

  #74 opened 3 years ago by Joywanglulu
  0

• DDPG on MountainCar

  #38 opened 4 years ago by gearsuccess
  2

• README link error

  #73 opened 3 years ago by JacobHA
  0

• Code lines missing in Mountain_Car.py

  #72 opened 3 years ago by saketadhau
  0

• Seeding in 'reset_game'

  #71 opened 3 years ago by Markus28
  1

• There is no implementation of a function update_next_state_reward_done_and_score in REINFORCE

  #37 opened 4 years ago by Jungmo
  1

• Action selection in Continuous Action Space

  #70 opened 3 years ago by sramakrishnan247
  0

• Visualize agent

  #69 opened 3 years ago by sramakrishnan247
  1

• TypeError: can't pickle _thread.RLock objects

  #44 opened 4 years ago by shuferhoo
  2

• Wrong parameter order

  #68 opened 3 years ago by leolyg
  0

• atari+sac_discrete, AttributeError: 'AtariEnv' object has no attribute 'reward_threshold'

  #67 opened 3 years ago by weiguowilliam
  0

• RuntimeError: cuda runtime error (801) : operation not supported at ..\torch/csrc/generic/StorageSharing.cpp:247

  #66 opened 3 years ago by zhouwy-lv
  0

• Calculate Entropy Tuning Loss in SAC/SAC Discrete

  #65 opened 3 years ago by xingdi-eric-yuan
  3

• Instructions require python 3.5-3.7

  #64 opened 3 years ago by gth828r
  0

• FileNotFoundError: [Errno 2] No such file or directory

  #45 opened 4 years ago by shuferhoo
  2

• Some questions abot Dueling DQN

  #36 opened 5 years ago by Yang-Yefeng
  1

• For SAC-discrete version, is it possible to update model with input of state and action just like Sac-continuous version?

  #62 opened 4 years ago by dbsxdbsx
  0

• Wrong temperature loss implementation for discrete SAC

  #61 opened 4 years ago by qiyan98
  2

• Sac Discrete Error

  #56 opened 4 years ago by sshillo
  4

• Overlap between first evaluation episode and "min_steps_before_learning" in SAC

  #59 opened 4 years ago by pvdsp
  0

• question on SAC for discrete action with temperature loss "alpha"

  #58 opened 4 years ago by dbsxdbsx
  1

• how to visualize the enviroment

  #29 opened 5 years ago by weixiang-95
  3

• Weight Initialization for SAC Discrete

  #53 opened 4 years ago by nageshky97s
  0

• Exception in CartPole with A2C: AttributeError: 'Process' object has no attribute 'kill'

  #51 opened 4 years ago by acriptis
  0

• RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #4 'mat1'

  #31 opened 5 years ago by Jeffrey28
  9

• Could not find a version that satisfies the requirement torch==0.4.1.post2

  #49 opened 4 years ago by tom-doerr
  0

• Actor output the wrong size in CartPole using PPO

  #42 opened 4 years ago by yaoxunji
  1

• suggestion

  #39 opened 4 years ago by m1996
  3

• strange results

  #41 opened 4 years ago by m1996
  0

• Dqn problem

  #40 opened 4 years ago by m1996
  2

• DDPG: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_addmm

  #33 opened 5 years ago by MeixinZhu
  2

• AttributeError: 'TimeLimit' object has no attribute 'get_score_to_win'

  #35 opened 5 years ago by olixu
  1

• Reproduce Discrete Soft Actor Critic in TF 2.0

  #34 opened 5 years ago by junhuang-ifast
  1

• Device problem for DDQN

  #32 opened 5 years ago by ierezell
  0

• ModuleNotFoundError: No module named 'nn_builder'

  #28 opened 5 years ago by BaiLiping
  2

• Can't run Fetch_Reach.py

  #30 opened 5 years ago by SieRaX
  1