Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / vwxyzjn/cleanrl issues and pull requests
#210 - Adding Average Reward PPO proposal
Issue -
State: closed - Opened by Howuhh over 2 years ago
- 3 comments
#208 - Remove the value function clipping
Issue -
State: closed - Opened by vwxyzjn over 2 years ago
#206 - PPO improvements
Issue -
State: closed - Opened by vwxyzjn over 2 years ago
#202 - License issues
Issue -
State: closed - Opened by vwxyzjn over 2 years ago
- 3 comments
#198 - PPO timeout proper handling
Issue -
State: open - Opened by Howuhh over 2 years ago
- 12 comments
#167 - Various minor PPO refactors
Issue -
State: closed - Opened by vwxyzjn over 2 years ago
- 1 comment
#155 - KeyError: "terminal_observation" in dqn.py
Issue -
State: closed - Opened by Jackory over 2 years ago
- 3 comments
#115 - Roadmap for CleanRL
Issue -
State: closed - Opened by vwxyzjn over 2 years ago
#100 - Prototype Envpool Support
Pull Request -
State: closed - Opened by vwxyzjn almost 3 years ago
- 6 comments
#99 - Update torch
Pull Request -
State: closed - Opened by vwxyzjn almost 3 years ago
- 1 comment
#98 - Downgrade setuptools
Pull Request -
State: closed - Opened by vwxyzjn almost 3 years ago
- 1 comment
#97 - vectorized c51 implementation based on vdqn
Pull Request -
State: closed - Opened by mniju almost 3 years ago
- 4 comments
#96 - This is a great job. I want to ask, how should you plot the following curves? seaborn or wandb? If use wandb, how to edit this? Thanks
Issue -
State: closed - Opened by caimingxue almost 3 years ago
- 1 comment
#95 - Clean up stale files
Pull Request -
State: closed - Opened by vwxyzjn almost 3 years ago
#94 - Add Gitpod support
Pull Request -
State: closed - Opened by vwxyzjn almost 3 years ago
- 2 comments
#93 - Reorganize README.md
Pull Request -
State: closed - Opened by vwxyzjn almost 3 years ago
#92 - Support github codespace
Pull Request -
State: closed - Opened by vwxyzjn almost 3 years ago
- 1 comment
#91 - Update paper citation entry
Pull Request -
State: closed - Opened by vwxyzjn almost 3 years ago
#90 - Set the correct SPOT allocation strategy
Pull Request -
State: closed - Opened by vwxyzjn almost 3 years ago
- 2 comments
#89 - add proper ppo entropy
Pull Request -
State: closed - Opened by 51616 almost 3 years ago
- 3 comments
#88 - Prepare for 0.5.0 release
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#87 - 0.5.0 Release preparation
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#86 - Bump tensorflow from 2.6.0 to 2.6.1 in /cleanrl/brax
Pull Request -
State: closed - Opened by dependabot[bot] about 3 years ago
- 1 comment
Labels: dependencies
#85 - Cloud utilities refactor
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#84 - Rollback back PyTorch version for better compatibility
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
- 1 comment
#83 - Add PPO Atari LSTM example
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
- 12 comments
#82 - Allow buildx to save to local and push
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#81 - Remove docker dummy cache
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#80 - Import built docker image to local registry
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
- 1 comment
#79 - Refactor value-based methods
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#78 - Refactor formats in `parse_args`
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#77 - Only run tests given changes to the `cleanrl` directory
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#76 - Add MuJoCo environments support.
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
- 1 comment
#75 - Fix #74 SAC consistency in logging and training to match other scripts
Pull Request -
State: closed - Opened by dosssman about 3 years ago
#74 - SAC Consistency
Issue -
State: closed - Opened by vwxyzjn about 3 years ago
#73 - Proper entropy regularized PPO
Issue -
State: closed - Opened by 51616 about 3 years ago
- 9 comments
#72 - Remove SB3 dependency in ppo_continuous_action.py
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#71 - Add pytest as an optional dependency
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#70 - Add e2e tests
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#69 - ddpg_continuous: Addded env argument to actor and target actor
Pull Request -
State: closed - Opened by dosssman about 3 years ago
- 1 comment
#68 - DDPG Actor missing 1 argument: 'env'
Issue -
State: closed - Opened by dosssman about 3 years ago
- 1 comment
#67 - Support Python 3.7.1+
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
- 1 comment
#66 - Make Spyder Editor Optional
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#65 - Cloud Utilities Improvement
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
- 2 comments
#64 - Prototype Documentation Site
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
- 2 comments
#63 - Prototype Support for Minihack
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#62 - Automatically Download Atari Roms
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
- 2 comments
#61 - Bump Gym's version to 0.21.0
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#60 - Bump Gym's version to 0.21.0
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#59 - Vectorized DQN Experiment
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
- 1 comment
#58 - Loading benchmarked hyperparams?
Issue -
State: closed - Opened by slerman12 about 3 years ago
- 2 comments
#57 - Documentation Site
Issue -
State: closed - Opened by vwxyzjn about 3 years ago
- 13 comments
#56 - Reorganization of files.
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
- 1 comment
#55 - Add paper plotting utilities
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
- 2 comments
#54 - Remove links to deleted code on README algorithms
Pull Request -
State: closed - Opened by FelipeMartins96 about 3 years ago
- 1 comment
#53 - Broken links on README
Issue -
State: closed - Opened by FelipeMartins96 about 3 years ago
- 2 comments
#52 - Mybranch
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#51 - Bump pillow from 8.3.1 to 8.3.2 in /cleanrl/brax
Pull Request -
State: closed - Opened by dependabot[bot] about 3 years ago
- 1 comment
Labels: dependencies
#50 - Use Poetry as the package manager
Pull Request -
State: closed - Opened by vwxyzjn about 3 years ago
#49 - LOMPO and COMBO implementation for visual offline RL
Issue -
State: closed - Opened by kargarisaac over 3 years ago
- 1 comment
#48 - Fix hyperlink to actually go to Weights and Biases
Pull Request -
State: closed - Opened by sudo-michael over 3 years ago
- 1 comment
#47 - Issues with applying PPO Impala on Retro Env in regards to running multiple environment
Issue -
State: closed - Opened by hlsafin over 3 years ago
- 20 comments
#46 - Dict observation space
Issue -
State: closed - Opened by jingxixu over 3 years ago
- 2 comments
#45 - Fixed typo
Pull Request -
State: closed - Opened by HelgeS over 3 years ago
#44 - Fix bibtex entry
Pull Request -
State: closed - Opened by jkterry1 over 3 years ago
#43 - AWS example?
Issue -
State: closed - Opened by drozzy over 3 years ago
- 2 comments
#42 - Video length increase for Procgen
Pull Request -
State: closed - Opened by bragajj over 3 years ago
#41 - BCQ Continuous
Pull Request -
State: closed - Opened by dosssman over 3 years ago
#40 - Fast ppg_procgen implementation
Pull Request -
State: closed - Opened by bragajj almost 4 years ago
#39 - Update ppo_procgen_fast.py
Pull Request -
State: closed - Opened by bragajj almost 4 years ago
- 2 comments
#38 - SAC CQL for continuous tasks.
Pull Request -
State: closed - Opened by dosssman almost 4 years ago
#37 - fix td3
Pull Request -
State: closed - Opened by chutaklee almost 4 years ago
- 1 comment
#36 - unify replay buffer
Pull Request -
State: closed - Opened by bentrevett about 4 years ago
- 1 comment
#35 - Both dqn_atari and dqn_atari_visual use different ReplayBuffers compared to other implementations
Issue -
State: closed - Opened by bentrevett about 4 years ago
- 5 comments
#34 - Refactoring on Class Arguments #27
Pull Request -
State: closed - Opened by adamcakg about 4 years ago
#33 - Work with AWS Preemptible Instance
Issue -
State: closed - Opened by vwxyzjn about 4 years ago
- 1 comment
Labels: enhancement, require expertise
#32 - Implementing PPG (Phasic Policy Gradient)
Issue -
State: closed - Opened by vwxyzjn about 4 years ago
- 2 comments
Labels: open rl benchmark, require expertise
#31 - Implementing IMPALA
Issue -
State: closed - Opened by vwxyzjn about 4 years ago
- 1 comment
Labels: enhancement, open rl benchmark, require expertise
#30 - Support StarCraft II Mini-game Environments (pysc2)
Issue -
State: closed - Opened by vwxyzjn about 4 years ago
Labels: help wanted, open rl benchmark
#29 - Support Procgen Environments
Issue -
State: closed - Opened by vwxyzjn about 4 years ago
Labels: help wanted, good first issue, open rl benchmark
#28 - Generally Support Griddly Environments
Issue -
State: closed - Opened by vwxyzjn about 4 years ago
Labels: open rl benchmark
#27 - Refactoring on Class Arguments
Issue -
State: closed - Opened by vwxyzjn about 4 years ago
- 3 comments
Labels: enhancement, help wanted, good first issue
#26 - TypeError: can't assign a list to a torch.cuda.FloatTensor
Issue -
State: closed - Opened by Kimonili about 4 years ago
- 8 comments
#25 - Add RND implementation
Pull Request -
State: closed - Opened by yooceii over 4 years ago
- 2 comments
#24 - PPO: Shouldn't advantages be recomputed after every minibatch update?
Issue -
State: closed - Opened by georgepsh over 4 years ago
- 2 comments
#23 - Possible mistake in normalization of returns
Issue -
State: closed - Opened by HamishDuncanson over 4 years ago
- 1 comment
#22 - Problems with PPO value loss
Issue -
State: closed - Opened by HamishDuncanson over 4 years ago
- 2 comments
#21 - Sac tweaks
Pull Request -
State: closed - Opened by dosssman over 4 years ago
#20 - GPU Implementation runs no faster than CPU counterparts
Issue -
State: closed - Opened by vwxyzjn over 4 years ago
- 3 comments
#19 - 0.3 Release
Issue -
State: closed - Opened by vwxyzjn over 4 years ago
#18 - Normalized Env Bug
Issue -
State: closed - Opened by vwxyzjn over 4 years ago
- 4 comments
#17 - Fix feature_turned_on count to account for KLE-Rollback. Safety check…
Pull Request -
State: closed - Opened by dosssman over 4 years ago
#16 - GAE bug with PPO2
Issue -
State: closed - Opened by vwxyzjn over 4 years ago
- 4 comments
#15 - PPO2 # fix value clipping
Pull Request -
State: closed - Opened by vwxyzjn over 4 years ago
- 2 comments
#14 - Cloud Integration Support
Issue -
State: closed - Opened by vwxyzjn over 4 years ago
#13 - Added layer norm to policy network and entropy bonus to policy loss.
Pull Request -
State: closed - Opened by dosssman over 4 years ago
#12 - This adds value loss clipping and Advantage normalization to ppo2_continuou_actions.
Pull Request -
State: closed - Opened by dosssman over 4 years ago
- 1 comment
#11 - Print out episode reward for debugging without tensorboard
Issue -
State: closed - Opened by vwxyzjn over 4 years ago
- 1 comment
#10 - GAE Calculation for PPO
Issue -
State: closed - Opened by vwxyzjn over 4 years ago
- 1 comment
#9 - Fixes the error where advantages were tensorized only in case the sampling was cut early.
Pull Request -
State: closed - Opened by dosssman over 4 years ago