rail-berkeley/rlkit issues and pull requests

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

Issue - State: closed - Opened by COST-97 over 4 years ago - 1 comment

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

Issue - State: closed - Opened by COST-97 over 4 years ago - 1 comment

#99 - key error when run_policy

Issue - State: closed - Opened by ChenyangRan over 4 years ago - 4 comments

#99 - key error when run_policy

Issue - State: closed - Opened by ChenyangRan over 4 years ago - 4 comments

#98 - Data overwritten in multitask_rollout

Issue - State: closed - Opened by HeinzBenjamin almost 5 years ago - 4 comments

#98 - Data overwritten in multitask_rollout

Issue - State: closed - Opened by HeinzBenjamin almost 5 years ago - 4 comments

#97 - Unusual MountainCarContinuous Results

Issue - State: closed - Opened by xxmissingnoxx almost 5 years ago - 4 comments

#97 - Unusual MountainCarContinuous Results

Issue - State: closed - Opened by xxmissingnoxx almost 5 years ago - 4 comments

#96 - Incomplete relabelling of trajectories in HER

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

#96 - Incomplete relabelling of trajectories in HER

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

#95 - How to deal with not converging with HER_SAC

Issue - State: open - Opened by YunchuZhang almost 5 years ago

#95 - How to deal with not converging with HER_SAC

Issue - State: open - Opened by YunchuZhang almost 5 years ago

#94 - about cuda error during replay weight

Issue - State: closed - Opened by YunchuZhang almost 5 years ago - 9 comments

#94 - about cuda error during replay weight

Issue - State: closed - Opened by YunchuZhang almost 5 years ago - 9 comments

#93 - "Forgetting Learning" using SAC in a Drone environment on PyRep

Issue - State: open - Opened by kaelgabriel almost 5 years ago - 2 comments

#93 - "Forgetting Learning" using SAC in a Drone environment on PyRep

Issue - State: open - Opened by kaelgabriel almost 5 years ago - 2 comments

#92 - UnicodeEncodeError

Issue - State: open - Opened by invisilmk almost 5 years ago - 3 comments

#92 - UnicodeEncodeError

Issue - State: open - Opened by invisilmk almost 5 years ago - 3 comments

#91 - No value function in Soft Actor Critic?

Issue - State: closed - Opened by KK666-AI almost 5 years ago - 1 comment

#91 - No value function in Soft Actor Critic?

Issue - State: closed - Opened by KK666-AI almost 5 years ago - 1 comment

#90 - Cannot render custom Gym environment "TypeError: 'bool' object is not callable"

Issue - State: closed - Opened by PierreExeter about 5 years ago - 3 comments

#90 - Cannot render custom Gym environment "TypeError: 'bool' object is not callable"

Issue - State: closed - Opened by PierreExeter about 5 years ago - 3 comments

#89 - Understanding the SAC paramters

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

#89 - Understanding the SAC paramters

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

#88 - Difference bewteen creating environments by different methods

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

#88 - Difference bewteen creating environments by different methods

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

#87 - why used two q function in sac?

Issue - State: closed - Opened by KK666-AI about 5 years ago - 1 comment

#87 - why used two q function in sac?

Issue - State: closed - Opened by KK666-AI about 5 years ago - 1 comment

#86 - seeds args in SAC

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

#86 - seeds args in SAC

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

#85 - question about the seed args

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

#85 - question about the seed args

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

#84 - self.custom_goal_sample is None

Issue - State: closed - Opened by Jingjinganhao about 5 years ago - 3 comments

#84 - self.custom_goal_sample is None

Issue - State: closed - Opened by Jingjinganhao about 5 years ago - 3 comments

#83 - 'ConvVAE' object has no attribute 'name'

Issue - State: closed - Opened by hieubkset about 5 years ago - 3 comments

#83 - 'ConvVAE' object has no attribute 'name'

Issue - State: closed - Opened by hieubkset about 5 years ago - 3 comments

#82 - General understanding: Purpose of evaluation in training

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

#82 - General understanding: Purpose of evaluation in training

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

#81 - SAC - can't pickle _thread.RLock objects

Issue - State: closed - Opened by cambel about 5 years ago - 3 comments

#81 - SAC - can't pickle _thread.RLock objects

Issue - State: closed - Opened by cambel about 5 years ago - 3 comments

#80 - Having SkewFit deal with stochastic environments

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

#80 - Having SkewFit deal with stochastic environments

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

#79 - VAE Reconstructions for Multiple Pucks

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

#79 - VAE Reconstructions for Multiple Pucks

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

#78 - Which commit of Doodad is rlkit using?

Issue - State: closed - Opened by Xingyu-Lin about 5 years ago - 3 comments

#78 - Which commit of Doodad is rlkit using?

Issue - State: closed - Opened by Xingyu-Lin about 5 years ago - 3 comments

#77 - No data file is being created and filed with new SAC trainings

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

#77 - No data file is being created and filed with new SAC trainings

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

#76 - distance in code ???

Issue - State: closed - Opened by vitiennam over 5 years ago - 1 comment

#76 - distance in code ???

Issue - State: closed - Opened by vitiennam over 5 years ago - 1 comment

#75 - alpha convergence issues with discrete actions

Issue - State: closed - Opened by wcarvalho over 5 years ago - 1 comment

#75 - alpha convergence issues with discrete actions

Issue - State: closed - Opened by wcarvalho over 5 years ago - 1 comment

#74 - Copy vs Deepcopy in SAC

Issue - State: open - Opened by richardrl over 5 years ago - 4 comments

#74 - Copy vs Deepcopy in SAC

Issue - State: open - Opened by richardrl over 5 years ago - 4 comments

#73 - SAC policy loss

Issue - State: closed - Opened by rmrafailov over 5 years ago - 1 comment

#73 - SAC policy loss

Issue - State: closed - Opened by rmrafailov over 5 years ago - 1 comment

#72 - Use torch.load in run_policy

Pull Request - State: closed - Opened by mihaic over 5 years ago

#72 - Use torch.load in run_policy

Pull Request - State: closed - Opened by mihaic over 5 years ago

#71 - Alpha loss bug?

Issue - State: closed - Opened by KeAWang over 5 years ago - 1 comment

#71 - Alpha loss bug?

Issue - State: closed - Opened by KeAWang over 5 years ago - 1 comment

#70 - unable to test the learnt model because customed_goal_sampler is not loaded

Issue - State: open - Opened by ZiwenZhuang over 5 years ago - 5 comments
Labels: bug

#70 - unable to test the learnt model because customed_goal_sampler is not loaded

Issue - State: open - Opened by ZiwenZhuang over 5 years ago - 5 comments
Labels: bug

#69 - where is the skew-fit coresponding code

Issue - State: closed - Opened by ZiwenZhuang over 5 years ago - 4 comments

#69 - where is the skew-fit coresponding code

Issue - State: closed - Opened by ZiwenZhuang over 5 years ago - 4 comments

#68 - This commit fixes #67

Pull Request - State: closed - Opened by vuoristo over 5 years ago

#68 - This commit fixes #67

Pull Request - State: closed - Opened by vuoristo over 5 years ago

#67 - Loading checkpoint trained on GPU on a CPU device fails.

Issue - State: closed - Opened by vuoristo over 5 years ago - 6 comments

#67 - Loading checkpoint trained on GPU on a CPU device fails.

Issue - State: closed - Opened by vuoristo over 5 years ago - 6 comments

#66 - Added linear scheduling option to epsilon greedy exploration

Pull Request - State: open - Opened by cdevin over 5 years ago

#66 - Added linear scheduling option to epsilon greedy exploration

Pull Request - State: open - Opened by cdevin over 5 years ago

#65 - Added linear scheduling option to epsilon greedy exploration

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

#65 - Added linear scheduling option to epsilon greedy exploration

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

#64 - FetchReach her example fails - easy to fix though

Issue - State: closed - Opened by MishaLaskin over 5 years ago - 1 comment

#64 - FetchReach her example fails - easy to fix though

Issue - State: closed - Opened by MishaLaskin over 5 years ago - 1 comment

#63 - Some benchmarks on six MuJoCo-v2 environments for DDPG and TD3

Issue - State: open - Opened by DanielTakeshi over 5 years ago - 3 comments

#63 - Some benchmarks on six MuJoCo-v2 environments for DDPG and TD3

Issue - State: open - Opened by DanielTakeshi over 5 years ago - 3 comments

#62 - Exception has occurred: AssertionError with Gym v0.12

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

#62 - Exception has occurred: AssertionError with Gym v0.12

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

#61 - install multiworld

Pull Request - State: closed - Opened by dwiel over 5 years ago

#61 - install multiworld

Pull Request - State: closed - Opened by dwiel over 5 years ago

#60 - dependency on multiworld even when not using it

Issue - State: closed - Opened by dwiel over 5 years ago - 4 comments

#60 - dependency on multiworld even when not using it

Issue - State: closed - Opened by dwiel over 5 years ago - 4 comments

#59 - Compatibility with pytorch 1.0

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

#59 - Compatibility with pytorch 1.0

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

#58 - DDPG example - Missing TorchRLAlgorithm, how to use BatchRLDatasetAlgorithm

Issue - State: closed - Opened by nm-narasimha over 5 years ago - 1 comment

GitHub / rail-berkeley/rlkit issues and pull requests