diff --git a/README.md b/README.md index 427799a..27d2d4e 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,7 @@ pip install mctx or you can install the latest development version from GitHub: ```sh -pip install git+https://github.com/deepmind/mctx.git +pip install git+https://github.com/google-deepmind/mctx.git ``` ## Motivation @@ -93,7 +93,7 @@ new_embedding)` with a `RecurrentFnOutput` and the embedding of the next state. The `RecurrentFnOutput` contains the `reward` and `discount` for the transition, and `prior_logits` and `value` for the new state. -In [`examples/visualization_demo.py`](https://github.com/deepmind/mctx/blob/main/examples/visualization_demo.py), you can +In [`examples/visualization_demo.py`](https://github.com/google-deepmind/mctx/blob/main/examples/visualization_demo.py), you can see calls to a policy: ```python @@ -110,11 +110,14 @@ We recommend to use the `gumbel_muzero_policy`. [Gumbel MuZero](https://openreview.net/forum?id=bERaNdoegnO) guarantees a policy improvement if the action values are correctly evaluated. The policy improvement is demonstrated in -[`examples/policy_improvement_demo.py`](https://github.com/deepmind/mctx/blob/main/examples/policy_improvement_demo.py). +[`examples/policy_improvement_demo.py`](https://github.com/google-deepmind/mctx/blob/main/examples/policy_improvement_demo.py). ### Example projects The following projects demonstrate the Mctx usage: +- [Pgx](https://github.com/sotetsuk/pgx) — A collection of 20+ vectorized + JAX environments, including backgammon, chess, shogi, Go, and an AlphaZero + example. - [Basic Learning Demo with Mctx](https://github.com/kenjyoung/mctx_learning_demo) — AlphaZero on random mazes. - [a0-jax](https://github.com/NTT123/a0-jax) — AlphaZero on Connect Four, diff --git a/setup.py b/setup.py index 957f93f..ec9891d 100644 --- a/setup.py +++ b/setup.py @@ -44,7 +44,7 @@ def _parse_requirements(path): setup( name='mctx', version=_get_version(), - url='https://github.com/deepmind/mctx', + url='https://github.com/google-deepmind/mctx', license='Apache 2.0', author='DeepMind', description=('Monte Carlo tree search in JAX.'),