wuisabel-gif/pokemon_tcg_ai_battle

Build a counterfactual prize-race evaluator about 3 hours ago

enhancement help wanted

0

Mega Lucario ex agent for the Kaggle PTCG AI Battle simulation competition, with a parallel Docker self-play test harness (confidence intervals), replay metagame mining, and a full-turn lookahead search agent.

Python

#agent#decision-making#game-ai#kaggle#mcts#monte-carlo-tree-search#pokemon-tcg#python#reinforcement-learning#self-play#simulation

Evaluate a hybrid MCTS policy about 3 hours ago

enhancement help wanted

wuisabel-gif/pokemon_tcg_ai_battle

0

Mega Lucario ex agent for the Kaggle PTCG AI Battle simulation competition, with a parallel Docker self-play test harness (confidence intervals), replay metagame mining, and a full-turn lookahead search agent.

Python

#agent#decision-making#game-ai#kaggle#mcts#monte-carlo-tree-search#pokemon-tcg#python#reinforcement-learning#self-play#simulation

Implement opponent archetype routing about 3 hours ago

enhancement help wanted

wuisabel-gif/pokemon_tcg_ai_battle

0

Mega Lucario ex agent for the Kaggle PTCG AI Battle simulation competition, with a parallel Docker self-play test harness (confidence intervals), replay metagame mining, and a full-turn lookahead search agent.

Python

#agent#decision-making#game-ai#kaggle#mcts#monte-carlo-tree-search#pokemon-tcg#python#reinforcement-learning#self-play#simulation

Connect the transformer model to bounded MCTS about 3 hours ago

enhancement help wanted

wuisabel-gif/pokemon_tcg_ai_battle

0

Mega Lucario ex agent for the Kaggle PTCG AI Battle simulation competition, with a parallel Docker self-play test harness (confidence intervals), replay metagame mining, and a full-turn lookahead search agent.

Python

#agent#decision-making#game-ai#kaggle#mcts#monte-carlo-tree-search#pokemon-tcg#python#reinforcement-learning#self-play#simulation

Train a behavior-cloning policy model about 3 hours ago

enhancement help wanted

wuisabel-gif/pokemon_tcg_ai_battle

0

Mega Lucario ex agent for the Kaggle PTCG AI Battle simulation competition, with a parallel Docker self-play test harness (confidence intervals), replay metagame mining, and a full-turn lookahead search agent.

Python

#agent#decision-making#game-ai#kaggle#mcts#monte-carlo-tree-search#pokemon-tcg#python#reinforcement-learning#self-play#simulation

Record local validation results about 3 hours ago

help wanted good first issue

wuisabel-gif/pokemon_tcg_ai_battle

0

Mega Lucario ex agent for the Kaggle PTCG AI Battle simulation competition, with a parallel Docker self-play test harness (confidence intervals), replay metagame mining, and a full-turn lookahead search agent.

Python

#agent#decision-making#game-ai#kaggle#mcts#monte-carlo-tree-search#pokemon-tcg#python#reinforcement-learning#self-play#simulation

Categorize public Kaggle notebooks about 3 hours ago

help wanted good first issue

wuisabel-gif/pokemon_tcg_ai_battle

0

Mega Lucario ex agent for the Kaggle PTCG AI Battle simulation competition, with a parallel Docker self-play test harness (confidence intervals), replay metagame mining, and a full-turn lookahead search agent.

Python

#agent#decision-making#game-ai#kaggle#mcts#monte-carlo-tree-search#pokemon-tcg#python#reinforcement-learning#self-play#simulation

Document replay JSON fields about 3 hours ago

help wanted good first issue

wuisabel-gif/pokemon_tcg_ai_battle

0

Mega Lucario ex agent for the Kaggle PTCG AI Battle simulation competition, with a parallel Docker self-play test harness (confidence intervals), replay metagame mining, and a full-turn lookahead search agent.

Python

#agent#decision-making#game-ai#kaggle#mcts#monte-carlo-tree-search#pokemon-tcg#python#reinforcement-learning#self-play#simulation

Add seat-performance chart about 3 hours ago

help wanted good first issue

wuisabel-gif/pokemon_tcg_ai_battle

0

Mega Lucario ex agent for the Kaggle PTCG AI Battle simulation competition, with a parallel Docker self-play test harness (confidence intervals), replay metagame mining, and a full-turn lookahead search agent.

Python

#agent#decision-making#game-ai#kaggle#mcts#monte-carlo-tree-search#pokemon-tcg#python#reinforcement-learning#self-play#simulation

Label 50 replay losses about 3 hours ago

help wanted good first issue

wuisabel-gif/pokemon_tcg_ai_battle

0

Mega Lucario ex agent for the Kaggle PTCG AI Battle simulation competition, with a parallel Docker self-play test harness (confidence intervals), replay metagame mining, and a full-turn lookahead search agent.

Python

#agent#decision-making#game-ai#kaggle#mcts#monte-carlo-tree-search#pokemon-tcg#python#reinforcement-learning#self-play#simulation

Open Issues Need Help