feat: Enhance README and add reinforcement learning example

- Updated README to include details on AI engine support and features, emphasizing the HUB protocol for external engine communication.
- Added a new section on compatible engines and their capabilities.
- Introduced a complete reinforcement learning example in `examples/reinforcement_learning.py`, demonstrating training a policy network using REINFORCE with self-play.
- Expanded documentation in `ai.rst` to reference the new RL example and its components.

Author: miskibin

docs/source/ai.rst

@@ -311,6 +311,24 @@ and its 180° rotation are strategically equivalent (with colors swapped):
     tensor = board.to_tensor()  # (4, 32)
     mask = board.legal_moves_mask()  # (1024,)
 
+Complete RL Example
+-------------------
+
+See ``examples/reinforcement_learning.py`` for a complete working example
+that trains a policy network using REINFORCE with self-play:
+
+.. code-block:: bash
+
+    pip install torch
+    python examples/reinforcement_learning.py
+
+The example includes:
+
+- Policy network (MLP) for move selection
+- Self-play game generation
+- REINFORCE training loop with discount returns
+- Evaluation against random baseline
+- Temperature annealing for exploration
 
 API Reference
 -------------