Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Overcooked

Benchmarks

Task NameDataset NameSOTA ResultTrend
CNOT minimizationOvercooked setting circuits
Avg CNOT Count3.52
26
CoordinationOvercooked Cramped Room layout v1
SP257
14
CoordinationOvercooked
Time43.53
14
Multi-agent coordinationOvercooked Coord. Ring
Average Return41.3
10
Human-Agent CoordinationOvercooked Multi-strategy Counter (human evaluation)
Average Score93.09
9
Human-Agent CoordinationOvercooked Counter Circuit (human evaluation)
Average Score91.11
9
Multi-agent coordinationOvercooked Overall
Return68.79
8
Multi-agent coordinationOvercooked Bothway Coord.
Return101.93
8
Multi-agent coordinationOvercooked Asymm. Adv.
Return134.01
8
Multi-agent coordinationOvercooked Counter Circ.
Return28.28
8
Multi-agent coordinationOvercooked Coord. Ring Multi-recipe
Return45.96
8
Zero-Shot CoordinationOvercooked Asymmetric Advantages layout v1
SP500
7
Zero-Shot CoordinationOvercooked Forced Coordination layout v1
SP200
7
Zero-Shot CoordinationOvercooked Coordination Ring layout v1
SP333
7
Zero-Shot CoordinationOvercooked Counter Circuit layout v1
SP Score246
7
CoordinationOvercooked Forced Coordination layout v1
SP200
7
CoordinationOvercooked Coordination Ring layout v1
SP333
7
CoordinationOvercooked Counter Circuit layout v1
SP246
7
Zero-Shot CoordinationOvercooked Unident_s environment (test)
Sparse Reward78.5
7
Zero-Shot CoordinationOvercooked Random0_Medium (test)
Shaped Reward146.1
7
Zero-Shot CoordinationOvercooked Random3 environment (evaluation)
Sparse Reward131.4
7
Zero-Shot CoordinationOvercooked Random3
Shaped Reward107.4
7
Zero-Shot CoordinationOvercooked Random0_Medium
Sparse Reward59.3
7
Multi-agent coordinationOvercooked cross-play official AI library
Time48.05
7
Multi-agent CoordinationOvercooked
IQM Return607.76
5
Showing 25 of 62 rows