v2.3.2

Overview

Full Changelog: v2.3.1...v2.3.2

Added

• Adds gradient cap for teacher student distillation by @alessandroassirelli98 in #91

Fixed

• Fixes unexpected keyword argument learning_rate within RandomNetworkDistillation by @ozhanozen in #87

New Contributors

• @alessandroassirelli98 made their first contribution in #91
• @ozhanozen made their first contribution in #87

v2.3.1

Overview

Full Changelog: v2.3.0...v2.3.1

Added

• Changes ETA to hh:mm:ss format by @renezurbruegg in #75

Fixed

• Fixes git repository code storage function by @Mayankm96 in #83
• Fixes padding shape in split_and_pad_trajectories to support arbitrary additional dimensions by @bikcrum in #77
• Disable distribution mean gradient propagation into action noise std for StudentTeacher by @flferretti in #82

New Contributors

• @renezurbruegg made their first contribution in #75
• @flferretti made their first contribution in #82

v2.3.0

Overview

RSL RL now supports distributed training. Additionally, a new distillation algorithm allows for student-teacher training.

Full Changelog: v2.2.4...v2.3.0

Added

• Adds Student-Teacher Distillation by @ClemensSchwarke in bbce4ef
• Adds Distillation for recurrent networks by @ClemensSchwarke in d3dbcc3
• Adds Multi-GPU training for PPO and Distillation by @Mayankm96 in 6f8460a

Fixed

• Changes WandB runner name to the log directory name by @Mayankm96 in b9f9e69
• Renames rnn_hidden_size to rnn_hidden_dim for naming consistency by @ClemensSchwarke

Breaking Changes

• Renamed actor_critic to policy to be more general and align with other architectures and algorithms by @ClemensSchwarke in bbce4ef

v2.2.4

Overview

Full Changelog: v2.2.3...v2.2.4

Fixed

• Accounts for start_iter when computing ETA by @PeterMitrano in #29
• Fixes parsing if rnd and symmetry configs not available by @pascal-roth in #72

New Contributors

• @PeterMitrano made their first contribution in #29
• @pascal-roth made their first contribution in #72

v2.2.3

Overview

This release adds some new parameters to PPO which help make the training more stable.

Full Changelog: v2.2.2...v2.2.3

Added

• Adds flag for per-batch advantage normalization by @Mayankm96 in #68
• Adds support for log-std parameter in ActorCritic by @Mayankm96 in #67

Fixed

• Fixes mean_entropy logging by dividing by num_updates by @bikcrum in #65
• Corrects disabling of arguments when creating Normal distribution by @Mayankm96 in #69

New Contributors

• @bikcrum made their first contribution in #65

v2.2.2

Overview

Full Changelog: v2.2.1...v2.2.2

Fixed

• Fixes bug in ActorCriticRecurrent hidden state reset by @jnskkmhr in #50
• Stops gradient propagation through ActorCritic std-dev by @Mayankm96 in #66
• Removes unused attributes from VecEnv in 8818338
• Fixes weight schedule dict for RND in 6909a47

New Contributors

• @jnskkmhr made their first contribution in #50

v2.2.0

Overview

This release adds the following additional features to our PPO implementation based on our research:

• Random Network Distillation (RND) - Encourages exploration by adding a curiosity driven intrinsic reward.
• Symmetry-based Augmentation - Makes the learned behaviors more symmetrical.

We thank the authors of these works for helping in adding these valuable contributions to the library.

Full Changelog: v2.1.2...v2.2.0

v2.1.2

Overview

A patch fix for local installation of the library. Previously, it was missing setup.py or setup.cfg which prohibited it from installation locally in editable mode. We have now added a dummy setup.py to fix this issue.

Full Changelog: v2.1.1...v2.1.2

v2.1.1

Overview

We’re excited to announce that the rsl-rl library is now available on PyPI! You can install it easily with:

pip install rsl-rl-lib

Full Changelog: v2.0.1...v2.1.1

Added

• Adds support for pip packaging by @kellyguo11 in #54
• Update license in all files and maintainers by @ClemensSchwarke in #56

Fixed

• Saves internal count of EmpiricalNormalization for resuming training by @tasdep in #30
• Fixes error caused by non UTF-8 characters in git diff by @fan-ziqi in #31

New Contributors

• @kellyguo11 made their first contribution in #54
• @ClemensSchwarke made their first contribution in #56
• @tasdep made their first contribution in #30
• @fan-ziqi made their first contribution in #31

Release v2.0.1

Overview

Full Changelog: v2.0.0...v2.0.1

Fixed

• Fixed RL device setting in the on policy runner
• Fixes issue with splitting and padding of trajectories for recurrent network architecture training
• Updates wandb and neptune logging by @Mayankm96 in #18