Overview
This release adds a new actor-critc class with CNN encoders for visual observations. It additionally refactors the rollout storage and seperates the logging functionality from the runner for better code clarity.
Full Changelog: v3.1.3...v3.2.0
Added
- Adds perceptive actor-critic class by @pascal-roth in #114
- Restructure rollout storage for clarity by @ClemensSchwarke in #137
- Separates the logging functionality from the runner by @ClemensSchwarke in #140
- Include run_name in training logs for better run traceability by @ShaoshuSu in #101
Fixed
- Remove unnecessary teacher eval call by @ClemensSchwarke in #139
- Add device for TensorDict in
split_and_pad_trajectoriesby @ClemensSchwarke in #138
New Contributors
- @ShaoshuSu made their first contribution in #101