google-deepmind/rlax v0.1.5

RLax 0.1.5

Repository: google-deepmind/rlax

Tag: v0.1.5

Published: 2023-01-09T13:23:23Z

Prerelease: no

Release notes:

What's Changed

• Replace for-loop in extract_subsequences with single indexing operation. by @copybara-service in https://github.com/deepmind/rlax/pull/98
• Replace O(n^2) iterative insert with linear append + reverse. by @copybara-service in https://github.com/deepmind/rlax/pull/99
• Expose utilities for constructing and learning from policy targets. by @copybara-service in https://github.com/deepmind/rlax/pull/106
• Add support for disabling stop_gradients on targets (as in other rlax losses). by @copybara-service in https://github.com/deepmind/rlax/pull/107
• [rlax] Update jax and numpy requirements for RLax. by @copybara-service in https://github.com/deepmind/rlax/pull/114
• Release new RLax version. by @copybara-service in https://github.com/deepmind/rlax/pull/115

Full Changelog: https://github.com/deepmind/rlax/compare/v0.1.4...v0.1.5