The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.
Get an email when there's a new version of RLax
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2022-08-15 | 3.3 kB | |
| RLax 0.1.4 source code.tar.gz | 2022-08-15 | 95.8 kB | |
| RLax 0.1.4 source code.zip | 2022-08-15 | 149.0 kB | |
| Totals: 3 Items | 248.2 kB | 0 | |
What's Changed
- rlax: Replace rlax categorical cross entropy computation with distrax components. by @copybara-service in https://github.com/deepmind/rlax/pull/57
- Bugfix to quantile_expected_sarsa. by @copybara-service in https://github.com/deepmind/rlax/pull/63
- Update Jinja2 versioning to avoid Sphinx failures. by @copybara-service in https://github.com/deepmind/rlax/pull/66
- Add test for squashed gaussian in rlax distributions. by @copybara-service in https://github.com/deepmind/rlax/pull/68
- Update squashed gaussian distribution in rlax for prob and logprob to numerically match distrax's implementation. by @copybara-service in https://github.com/deepmind/rlax/pull/69
- Migrate RLax squashed gaussian to use Distrax. Explicitly broadcast shapes in Distrax scalar affine to avoid rank promotion errors. by @copybara-service in https://github.com/deepmind/rlax/pull/70
- Add a particular pair of transforms used by muzero that combine a non linear squashing function with a reparametrisation of the scalar as linear combination of two hot values in a discrete suppport. by @copybara-service in https://github.com/deepmind/rlax/pull/73
- Support Array lambda_ in Vtrace. by @copybara-service in https://github.com/deepmind/rlax/pull/71
- Send deprecation warning for rlax.distributions in favor of using distrax. by @copybara-service in https://github.com/deepmind/rlax/pull/74
- Send deprecation warning for rlax nested_updates in favor of using optax. by @copybara-service in https://github.com/deepmind/rlax/pull/75
- Move usages of soon to be deprecated rlax.periodic_update to optax.periodic_update. by @copybara-service in https://github.com/deepmind/rlax/pull/77
- Add a pair of transforms where the scalar values are reparametrised as the linear combination of two-hot values on a non-linearly spaced discrete support. by @copybara-service in https://github.com/deepmind/rlax/pull/78
- Add moving averages helpers to rlax. by @copybara-service in https://github.com/deepmind/rlax/pull/79
- Update .pylintrc by @copybara-service in https://github.com/deepmind/rlax/pull/80
- Add utilities to extract overlapping subsequences from trajectories. by @copybara-service in https://github.com/deepmind/rlax/pull/81
- Minor edits to moving averages. by @copybara-service in https://github.com/deepmind/rlax/pull/83
- Add utilities to support interruptions. by @copybara-service in https://github.com/deepmind/rlax/pull/84
- Create new version 0.1.3 of RLax. by @copybara-service in https://github.com/deepmind/rlax/pull/86
- Remove incremental_update from rlax: all usages ported to optax.incremental_update by @copybara-service in https://github.com/deepmind/rlax/pull/85
- Pin numpy version <1.23 until new jax version is released, fixing bug that makes mpo_ops_test fail. by @copybara-service in https://github.com/deepmind/rlax/pull/92
- Fix a bug in tree_split_leaves(): squeeze the right axis in case of keepdim=False. by @copybara-service in https://github.com/deepmind/rlax/pull/94
- Fix max_start_idx argument. by @copybara-service in https://github.com/deepmind/rlax/pull/87
- Release a new rlax verison. by @copybara-service in https://github.com/deepmind/rlax/pull/96
Full Changelog: https://github.com/deepmind/rlax/compare/v0.1.2...v0.1.4