pokemonai
pokemonai copied to clipboard
Reinforcement learning approach to playing competitive Pokémon.
Pokémon AI 
Goal
Reinforcement learning approach to playing competitive Pokémon. Battling is done on Smogon's Pokémon Showdown! battle simulator.
Ideas to Explore
- Batch RL (experience replay/fitted Q iteration)
- Online TD Learning
- PG methods (DDPG)
- Monte Carlo Tree Search (with simplfied assumptions)
- Imitation learning with Smogon leaderboard