Reinforcement Learning

Transformer Architectures as Policy Networks in Game Domains

Self-attention lets game AIs link distant board positions without recurrent bottlenecks.

October 21, 20269 min read

October 15, 20269 min read

Reinforcement Learning

October 14, 202610 min read

Reinforcement Learning

Deja Whitmore-CastilloOctober 13, 202610 min read

Reinforcement Learning

Layering policies shortens planning horizons and splits credit assignment in long-horizon games.

Svetlana ŘehořováOctober 10, 20269 min read

Reinforcement Learning

Model-based RL wins on sample efficiency; model-free RL handles complex environments better.

Deja Whitmore-CastilloOctober 9, 202611 min read