"Deep Learning Meets Deep Strategy" - Chess AI agent using reinforcement learning (RL) for academic tournament. Implements Q-learning/MCTS/policy gradients with 2s move constraints. CPU-only, inherits from provided Agent interface. Self-play training with neural networks for competitive chess gameplay.
python machine-learning chess-engine reinforcement-learning deep-learning tournament q-learning pytorch artificial-intelligence mcts neural-networks policy-gradient academic-project chess-ai self-play competitive-ai
-
Updated
Oct 21, 2025 - Python