Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / HumanCompatibleAI/imitation issues and pull requests
#865 - Detached2
Pull Request -
State: closed - Opened by leonthorm 29 days ago
#864 - GAIL is not trainig with image-based data
Issue -
State: open - Opened by aha85b about 1 month ago
Labels: bug
#863 - Code example to log to wandb using your custom logger
Issue -
State: open - Opened by Butanium about 1 month ago
Labels: enhancement
#862 - Continue training of a BC policy with RL fails
Issue -
State: open - Opened by timosturm 2 months ago
- 1 comment
Labels: bug
#861 - AssertionError: Tuple observations are not supported.
Issue -
State: open - Opened by AcademeMaster 3 months ago
Labels: bug
#860 - `transitions_collate_fn` expects `next_obs` from `TransitionsMinimal`
Issue -
State: open - Opened by namheegordonkim 4 months ago
Labels: bug
#859 - How to Retrieve mean/gen/train/loss during GAIL Training and Create Checkpoints on New Minimum
Issue -
State: open - Opened by kechirojp 4 months ago
Labels: bug
#858 - Fix inability to load FeedForward32Policy
Pull Request -
State: open - Opened by glolichen 7 months ago
#857 - Unable to load FeedForward32Policy -- multiple values for keyword argument 'net_arch'
Issue -
State: open - Opened by glolichen 7 months ago
- 1 comment
Labels: bug
#856 - Robust termination Condition for equal horizon episodes
Issue -
State: open - Opened by abastola0 7 months ago
Labels: bug
#855 - Fix PosixPath being passed to HuggingFace `save_to_disk` (which does not accept it)
Pull Request -
State: open - Opened by iwishiwasaneagle 7 months ago
- 1 comment
#854 - "The observation_space and action_space were not given, can't verify new environments" when loading expert policy
Issue -
State: open - Opened by boshi-an 7 months ago
- 2 comments
Labels: bug
#853 - GAIL tensorboard logging does not appear to work
Issue -
State: open - Opened by eufrizz 8 months ago
Labels: bug
#852 - TypeError: argument of type 'PosixPath' is not iterable
Issue -
State: closed - Opened by den-schmidt 9 months ago
- 2 comments
Labels: bug
#851 - Serialize Dataset Save Not Working
Issue -
State: open - Opened by alexpalms 9 months ago
- 1 comment
Labels: bug
#850 - Problem in Passing Along Custom Gym Env Constructor Parameters in make_vec_env
Issue -
State: open - Opened by christianjcc 9 months ago
- 1 comment
Labels: bug
#849 - Adding More State Only Imitation Learning Algorithms
Issue -
State: open - Opened by HridayM25 10 months ago
Labels: enhancement
#848 - Preference based Reinforcement Learning applies a "recurrent reward network" for solving a POMDP problem
Issue -
State: open - Opened by CAI23sbP 10 months ago
Labels: enhancement
#847 - gen_replay_buffer_capacity VS demo_batch_size in tutorials code
Issue -
State: open - Opened by piteren 10 months ago
Labels: bug
#846 - difference between Step and Sample in Dagger
Issue -
State: open - Opened by lwizard1999 10 months ago
#845 - segmentation fault while loading policy
Issue -
State: closed - Opened by chenyangkang 11 months ago
- 1 comment
Labels: bug
#844 - abort and kernel crash with OMP libomp.dylib
Issue -
State: closed - Opened by chenyangkang 11 months ago
- 1 comment
Labels: bug
#843 - Device conflict when training BC
Issue -
State: open - Opened by IsaacSheidlower 11 months ago
- 1 comment
Labels: bug
#842 - Fix excessive RAM usage of preference comparisons
Pull Request -
State: open - Opened by timokau 11 months ago
#841 - Tuning code for PC and SQIL
Pull Request -
State: open - Opened by ernestum 12 months ago
#840 - Rewards visualization
Issue -
State: open - Opened by Rajesh-Siraskar 12 months ago
Labels: enhancement
#839 - [Question] Training in Custom Environment
Issue -
State: closed - Opened by KingsDevs 12 months ago
Labels: enhancement
#838 - [Question] Reward net transfer
Issue -
State: open - Opened by risufaj about 1 year ago
- 1 comment
#837 - Fix variable horizon link in 4_train_airl.ipynb
Pull Request -
State: open - Opened by Ivan-267 about 1 year ago
- 1 comment
#836 - RewardNetwork predict_processed doesn't work without next_state and done
Issue -
State: open - Opened by gustavodemari about 1 year ago
- 1 comment
Labels: bug
#835 - Integration of Rule-Based Bot Actions for Imitation Learning
Issue -
State: open - Opened by vladyskai about 1 year ago
- 2 comments
Labels: enhancement
#834 - Hierarchical Behavior Cloning
Issue -
State: open - Opened by Dhanushvarma about 1 year ago
Labels: enhancement
#833 - RILE file is created by copying AIRL file
Pull Request -
State: closed - Opened by mertalbaba about 1 year ago
#832 - PC Benchmarks
Pull Request -
State: open - Opened by ernestum about 1 year ago
- 1 comment
#831 - Ensure safe_to_tensor moves tensors to the specified device.
Pull Request -
State: closed - Opened by ernestum about 1 year ago
- 7 comments
#830 - Fix coverage issue in BC tests
Pull Request -
State: closed - Opened by ernestum about 1 year ago
- 3 comments
#829 - Remove FloatReward
Pull Request -
State: closed - Opened by ernestum about 1 year ago
- 5 comments
#828 - Make the default device for policies "cpu"
Pull Request -
State: closed - Opened by ernestum about 1 year ago
- 5 comments
#827 - Fix documentation pipeline
Pull Request -
State: closed - Opened by ernestum about 1 year ago
- 2 comments
#826 - Switch to lualatex to generate the documentation PDF
Pull Request -
State: closed - Opened by ernestum about 1 year ago
- 1 comment
#825 - Run time Error when run quickstart.py
Issue -
State: closed - Opened by Charles-Lim93 about 1 year ago
- 1 comment
Labels: bug
#824 - Clarify in README.md that we switched to gymnasium.
Pull Request -
State: closed - Opened by ernestum about 1 year ago
- 4 comments
#823 - Fix warning in quickstart.py
Pull Request -
State: closed - Opened by ernestum about 1 year ago
- 5 comments
#822 - Add more benchmarking documentation
Pull Request -
State: closed - Opened by ernestum about 1 year ago
- 2 comments
#821 - SyntheticGatherer often gives nearly deterministic feedback
Issue -
State: open - Opened by timokau about 1 year ago
- 1 comment
Labels: bug
#820 - Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
Issue -
State: closed - Opened by kavinwkp over 1 year ago
- 3 comments
Labels: bug
#819 - The observation_space and action_space were not given, can't verify new environments
Issue -
State: closed - Opened by kavinwkp over 1 year ago
- 3 comments
Labels: bug
#818 - Tensorboard Logging
Issue -
State: closed - Opened by mertalbaba over 1 year ago
- 1 comment
Labels: enhancement
#817 - Update the README files
Pull Request -
State: closed - Opened by ernestum over 1 year ago
#816 - Example notebook "1_train_bc.ipynb" gives "Namespace not found error" for "seals" module
Issue -
State: closed - Opened by Rajesh-Siraskar over 1 year ago
- 3 comments
Labels: bug
#815 - Examples Don't work
Issue -
State: closed - Opened by AdvanceXplorer over 1 year ago
- 4 comments
Labels: bug
#814 - DAgger Demo Code not working
Issue -
State: closed - Opened by nil123532 over 1 year ago
- 2 comments
Labels: bug
#813 - IQ-Learn
Issue -
State: closed - Opened by azafar1991 over 1 year ago
- 1 comment
Labels: enhancement
#812 - Running benchmarks
Pull Request -
State: closed - Opened by ernestum over 1 year ago
- 3 comments
#811 - SQIL and PC performance check fixes
Pull Request -
State: closed - Opened by ernestum over 1 year ago
- 2 comments
#810 - Reduce training time and improve expert loading code in the tutorials
Pull Request -
State: closed - Opened by ernestum over 1 year ago
#809 - error with setting up reward net
Issue -
State: closed - Opened by spearsheep over 1 year ago
- 1 comment
Labels: bug
#808 - Trained reward function outputs constant zeros using MCE algorithm
Issue -
State: closed - Opened by spearsheep over 1 year ago
- 1 comment
Labels: bug
#807 - Fix flaky SQIL test
Issue -
State: closed - Opened by AdamGleave over 1 year ago
Labels: bug
#806 - Update gymnasium dependency and render_mode in gym.make
Pull Request -
State: closed - Opened by taufeeque9 over 1 year ago
- 1 comment
#805 - Mceirl train
Pull Request -
State: open - Opened by ZiyueWang25 over 1 year ago
#804 - ReadTimeout during hyperparameter tuning
Issue -
State: closed - Opened by ZiyueWang25 over 1 year ago
- 1 comment
Labels: bug
#803 - Ensure MyST-NB raises an error when rendering a notebook fails.
Pull Request -
State: closed - Opened by ernestum over 1 year ago
#802 - Add rgb observation to dagger
Pull Request -
State: open - Opened by ZiyueWang25 over 1 year ago
- 3 comments
#801 - Upgrade pytype
Pull Request -
State: closed - Opened by ZiyueWang25 over 1 year ago
- 1 comment
#800 - Remove MuJoCo dependency from SQIL notebook
Pull Request -
State: closed - Opened by AdamGleave over 1 year ago
- 4 comments
#799 - Notebooks failing in readthedocs build does not trigger red status
Issue -
State: closed - Opened by AdamGleave over 1 year ago
- 2 comments
Labels: bug
#798 - Update 8a_train_sqil_sac.ipynb to remove MuJoCo dependency
Issue -
State: closed - Opened by AdamGleave over 1 year ago
Labels: bug
#797 - Fix MacOS Pipeline: Include tests not in subdirectories
Pull Request -
State: closed - Opened by AdamGleave over 1 year ago
- 2 comments
#796 - Part of solution to #795: add HumanReadableWrapper
Pull Request -
State: closed - Opened by ZiyueWang25 over 1 year ago
- 1 comment
#795 - Add rgb observation to obs for interactive policy prediction
Issue -
State: open - Opened by ZiyueWang25 over 1 year ago
Labels: enhancement
#794 - Remove FloatReward when next SB3 is released
Issue -
State: closed - Opened by ZiyueWang25 over 1 year ago
Labels: enhancement
#793 - Shorten timeout and ensure the notebook can still show desired improvement.
Issue -
State: closed - Opened by ZiyueWang25 over 1 year ago
Labels: enhancement
#792 - Notebook fix
Pull Request -
State: closed - Opened by ZiyueWang25 over 1 year ago
- 3 comments
#791 - tests/algorithms/test_sqil.py::test_sqil_performance_continuous[DDPG] failure
Issue -
State: closed - Opened by ZiyueWang25 over 1 year ago
- 1 comment
Labels: bug
#790 - Mismatch between Tutorial doc and the actual jupyter notebook
Issue -
State: closed - Opened by ZiyueWang25 over 1 year ago
- 1 comment
Labels: bug
#789 - Improve pipeline speed and abort early
Issue -
State: open - Opened by ernestum over 1 year ago
Labels: enhancement
#788 - Observation space not supported when getting expert trajectories in tutorial 7
Issue -
State: closed - Opened by camberg23 over 1 year ago
- 3 comments
Labels: bug
#787 - Script for running a hyperparameter sweep for sqil
Pull Request -
State: closed - Opened by lukasberglund over 1 year ago
- 1 comment
#786 - Add support for SB3 callbacks in adversarial training
Pull Request -
State: open - Opened by smanolloff over 1 year ago
- 1 comment
#785 - Add partial support for dictionary observation spaces (bc, density)
Pull Request -
State: closed - Opened by NixGD over 1 year ago
- 8 comments
#784 - Add CLI for SQIL
Pull Request -
State: closed - Opened by lukasberglund over 1 year ago
Labels: enhancement
#783 - Consider allowing integer reward in trajectories
Issue -
State: open - Opened by PavelCz over 1 year ago
Labels: enhancement
#782 - Complete PR #771 (Tune preference comparison example hyperparameters)
Pull Request -
State: closed - Opened by lukasberglund over 1 year ago
- 2 comments
#781 - Got an unexpected keyword argument 'use_sde' when passing behavioural cloning policy to PPO from SB3
Issue -
State: open - Opened by JkAcktuator over 1 year ago
- 7 comments
Labels: bug
#780 - Add CLI for SQIL
Issue -
State: closed - Opened by AdamGleave over 1 year ago
- 2 comments
Labels: enhancement
#779 - Add a test timeout
Pull Request -
State: closed - Opened by ernestum over 1 year ago
- 12 comments
#778 - Add an option to run SQIL with various off-policy algorithms
Pull Request -
State: closed - Opened by zajaczajac over 1 year ago
#777 - Utilizing Expert Data (.npz) in format of SB3.
Issue -
State: open - Opened by azafar1991 over 1 year ago
- 5 comments
Labels: enhancement
#776 - Introduce interactive policies to gather data from a user
Pull Request -
State: closed - Opened by zajaczajac over 1 year ago
#775 - Dependency fixes
Pull Request -
State: open - Opened by ernestum over 1 year ago
#774 - Tune hyperparameters for kernel density estimation tutorial
Pull Request -
State: open - Opened by zajaczajac over 1 year ago
Labels: docs
#773 - Add huggingface_sb3<=2.2.5 version requirement
Pull Request -
State: closed - Opened by zajaczajac over 1 year ago
#772 - Tune hyperparameters in tutorials for GAIL and AIRL
Pull Request -
State: open - Opened by zajaczajac over 1 year ago
Labels: docs
#771 - Tune preference comparison example hyperparameters
Pull Request -
State: closed - Opened by timokau over 1 year ago
- 3 comments
#770 - Adversarial algorithm matching original paper's implementation
Pull Request -
State: open - Opened by taufeeque9 over 1 year ago
- 1 comment
#769 - Add scripts for type-checking rst doc files and Jupyter notebooks
Pull Request -
State: open - Opened by jas-ho over 1 year ago
- 1 comment
#768 - Use data acquired by users
Pull Request -
State: closed - Opened by jas-ho over 1 year ago
- 1 comment
#767 - Generalize SQIL to work with other off-policy algos
Issue -
State: closed - Opened by jas-ho over 1 year ago
- 2 comments
Labels: enhancement
#766 - Download experts from hf inside tutorials and docs
Pull Request -
State: closed - Opened by jas-ho over 1 year ago
- 5 comments