SOTA Game Playing benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
Go (round-robin)	AR-BTS	Avg Trials per Move5,375	30	4mo ago
AtariGo	MCPS	Winrate69	24	1mo ago
Balatro In-distribution seeds	DemoEvolve	Capped Mean Final Round24	16	2mo ago
Atari 2600 (Arcade Learning Environment) v1 (test)	Human	Alien Score6,875	13	4mo ago
Biased RPS Standard (test)	PPO-EMAg	Exploitability17.9	12	1mo ago
Balatro Out-of-distribution seeds	DemoEvolve	Capped Mean Final Round24	12	2mo ago
Fighting Game against Ryu AI levels 1-8		Win Rate vs Ryu AI100	10	2mo ago
Goofspiel Standard Benchmarks (test)	PPO-EMAg	Exploitability0.007	8	1mo ago
Yahtzee Full-game 100,000 evaluation games		Mean Score254.59	8	4mo ago
Atari 12 unseen games		AirRaid1,125	8	4mo ago
Simple Negotiation		Win Rate46.2	7	4mo ago
KuhnPoker	Multi-Game Model	Win Rate53.9	7	4mo ago
TicTacToe	TicTacToe Specialist	Win Rate56.6	7	4mo ago
Leduc Poker	QL	Raw Reward3.5	6	2mo ago
Kuhn Poker	QL	Raw Reward0.98	6	2mo ago
Average	Multi-Game Model	Win Rate59.5	6	4mo ago
Truth and Deception	Multi-Game Model	Win Rate84	6	4mo ago
Pig Dice	Multi-Game Model	Win Rate99.8	6	4mo ago
Snake	Multi-Game Model	Win Rate31.6	6	4mo ago
Atari 2600 Seaquest HEAD	GRAIL	Mean Game Score501.6	5	2mo ago
3x3 2-Player	Solly	Solly Win %60	5	2mo ago
DOOM defend_the_center real-time pacing	SLM-Doom-MV-1.3M	Average Survival Time388	5	3mo ago
Atari 33 seen games	MCTR w/o RL&MR	Game Score: Alien10,160	5	4mo ago
Control Games Kuhn (test)	PPO-EMAg	Exploitability0.032	4	1mo ago
Control Goofspiel (test)	PPO-EMAg	Exploitability0.105	4	1mo ago

Showing 25 of 45 rows