rail-berkeley/rlkit

Issues

• Download link is expired

  #174 opened 4 months ago by deepneuralnetworks
  2

• IQL results different with the paper

  #172 opened 2 years ago by dssrgu
  1

• SAC log_alpha different from paper

  #171 opened 2 years ago by cvigoe
  1

• Python3.5 is not suitable for this project!

  #169 opened 2 years ago by ZhenhuiTang
  1

• AWAC doesn't profit from offline data

  #166 opened 2 years ago by im-Kitsch
  4

• Reproduce and create figures results in AWAC.

  #173 opened a year ago by linhlpv
  0

• Visualizing the Training and Running the Trained Policy using RIG

  #121 opened 4 years ago by amir-ramezani-ai
  6

• Could someone provide right environment installation procedure?

  #168 opened 2 years ago by ZhenhuiTang
  4

• Why I could not see result file？

  #170 opened 2 years ago by ZhenhuiTang
  0

• Difficulty Reproducing HalfCheetah-v2 SAC Results

  #128 opened 4 years ago by xanderdunn
  6

• IQL: make checkpoints public

  #167 opened 2 years ago by ezhang7423
  0

• Skew-fit gaussian_identity_variance

  #165 opened 2 years ago by NoListen
  0

• High Memory & Disk Requirement for SMAC

  #164 opened 2 years ago by ShayekhBinIslam
  1

• Cannot reproduce the results of IQL on antmaze

  #163 opened 3 years ago by Shenzhi-Wang
  1

• Position Control with mujoco-py

  #161 opened 3 years ago by bara-bba
  0

• Doubt on advantage calculation to update the policy on AWAC.

  #160 opened 3 years ago by Roberto09
  0

• CustomMDPPathCollector is not found

  #159 opened 3 years ago by Shinntarou
  2

• Doubt on Q-function loss in AWAC

  #149 opened 3 years ago by Roberto09
  1

• Question about VAEPolicy in rlkit.torch.sac.policies

  #158 opened 3 years ago by HYDesmondLiu
  2

• There is no "CustomMDPPathCollector" anywhere...

  #140 opened 3 years ago by HYDesmondLiu
  1

• rlkit/torch/networks/stochastic not installed

  #144 opened 3 years ago by alipi
  1

• multi-GPU optimised implementations for running algorithms

  #148 opened 3 years ago by shivanimall
  1

• unable to create the conda environment with linux-cpu-env.yml

  #145 opened 3 years ago by Superyoutiao
  2

• Issue SMAC algorithm

  #146 opened 3 years ago by ijmarrero
  4

• Upgrade PyTorch

  #127 opened 4 years ago by xanderdunn
  3

• launch different seeds simulateously

  #106 opened 4 years ago by ChenyangRan
  4

• AWAC loss function

  #130 opened 3 years ago by DuaneNielsen
  3

• bug in tanhcnngaussianpolicy

  #139 opened 3 years ago by Yuichi-Nakababayashi
  0

• collect_new_paths in mdppathcollector

  #138 opened 3 years ago by Yuichi-Nakababayashi
  0

• Default GPU Yaml file fails

  #124 opened 4 years ago by richardrl
  4

• AWAC: cannot reproduce result in the paper

  #136 opened 3 years ago by bmbyzy
  0

• Compatible with Windows system？

  #135 opened 3 years ago by AmyWorkspace
  1

• evaluation/env_infos/failed Mean = 0.0

  #133 opened 3 years ago by liuqi8827
  2

• Cannot reshape array in function dump_video (video.py)

  #131 opened 3 years ago by sandipan1
  1

• Code for generating results figures?

  #123 opened 4 years ago by avandekleut
  1

• About desired_goal, state_desired_goal

  #132 opened 3 years ago by BillHan-Fantast
  0

• cannot import name 'FlattenMlp'

  #129 opened 4 years ago by chenci107
  1

• Final Distance in Push

  #126 opened 4 years ago by MianchuWang
  4

• TypeError: can't pickle _thread.lock objects

  #125 opened 4 years ago by refalguera
  0

• AWACTrainer is just an implementation of AWR algorithm?

  #122 opened 4 years ago by vinowan
  0

• Why is goal_sampling_mode='vae_prior' in Skew-Fits sawyer_push config?

  #118 opened 4 years ago by mseitzer
  2

• MSE reconstruction loss in VAE training is summed over, not averaged over

  #119 opened 4 years ago by mseitzer
  3

• New tag for version before AWAC commit

  #117 opened 4 years ago by ksluck
  2

• [solved] ResolvePackageNotFound error when installing the conda environment

  #107 opened 4 years ago by PierreExeter
  1

• How to log performance metrics when evaluating a trained policy?

  #108 opened 4 years ago by PierreExeter
  2

• Issue with reproducibility

  #102 opened 4 years ago by RushikeshJoshi4
  2

• Skew fit on non visual based environments?

  #104 opened 4 years ago by thibautlavril
  0

• Can't run trained policy because there's an issue with loading the models.

  #103 opened 4 years ago by MhmdGaffar
  0

• Trying to run_policy.py while also run_sac.py

  #101 opened 4 years ago by nanbaima
  1

• couldn't find the core code file that implements "Skew-Fit".

  #100 opened 5 years ago by COST-97
  1