Add a link to Pgx - a collection of 20+ JAX environments.

Fixes #65.

PiperOrigin-RevId: 569229226

README.md

@@ -21,7 +21,7 @@ pip install mctx
 or you can install the latest development version from GitHub:
 
 ```sh
-pip install git+https:/deepmind/mctx.git
+pip install git+https:/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:/deepmind/mctx/blob/main/examples/visualization_demo.py), you can
+In [`examples/visualization_demo.py`](https:/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:/deepmind/mctx/blob/main/examples/policy_improvement_demo.py).
+[`examples/policy_improvement_demo.py`](https:/google-deepmind/mctx/blob/main/examples/policy_improvement_demo.py).
 
 ### Example projects
 The following projects demonstrate the Mctx usage:
 
+- [Pgx](https:/sotetsuk/pgx) — A collection of 20+ vectorized
+ JAX environments, including backgammon, chess, shogi, Go, and an AlphaZero
+ example.
 - [Basic Learning Demo with Mctx](https:/kenjyoung/mctx_learning_demo) —
  AlphaZero on random mazes.
 - [a0-jax](https:/NTT123/a0-jax) — AlphaZero on Connect Four,

setup.py

@@ -44,7 +44,7 @@ def _parse_requirements(path):
 setup(
  name='mctx',
  version=_get_version(),
- url='https:/deepmind/mctx',
+ url='https:/google-deepmind/mctx',
  license='Apache 2.0',
  author='DeepMind',
  description=('Monte Carlo tree search in JAX.'),