coax
coax copied to clipboard
coax-dev
Modular framework for Reinforcement Learning in python
This PR adds type annotations to `coax`. Closes https://github.com/coax-dev/coax/issues/13
This issue tracks the progress of adding type annotations to `coax`. - [ ] `_core` - [ ] `experience_replay` - [ ] `model_updaters` - [ ] `policy_objectives` - [ ]...
This issue tracks the progress of converting the [numpy style](https://numpydoc.readthedocs.io/en/latest/format.html#docstring-standard) docstrings to the more concise [Google style](https://google.github.io/styleguide/pyguide.html#381-docstrings). - [ ] `_core` - [ ] `experience_replay` - [ ] `model_updaters` -...
**Describe the bug** Hey Kris, love your framework! Working with a custom environment, and your discrete action unit test works perfect locally. Don't spend much time investigating this yet, just...
This PR is a rework of https://github.com/coax-dev/coax/pull/26 and adds an example for using `SAC` on the `Walker.walk` task from the DeepMind Control Suite. Depends on https://github.com/coax-dev/coax/pull/27 and https://github.com/coax-dev/coax/pull/28
This PR updates the requirements, wrappers and examples to the new API introduced by `gym==0.26.0`. Depends on https://github.com/coax-dev/coax/pull/27
This PR resolves some warnings connected to deprecations in the Jax API.
Just wondering if there are any example of using this lib for implement RLHF (Reinforcement Learning from Human Feedback)? Inspired by: https://openai.com/blog/chatgpt  Many thanks for any help! :)
**Is your feature request related to a problem? Please describe.** It seems that the implemented replay buffers only operate over transitions, with no ability to operate over entire sequences. This...
How would you implement a minimax q-learner with coax? Hi there! I love the package and how accessible it is to relative newbies. The tutorials are pretty great and the...
