List your company

ResearchFormerly WizWand

GRF

Benchmarks

TaskDatasetSOTA resultTrendResults

Strategy Discovery

GRF 3v1

5.7Distinct Strategies

11

Multi-agent reinforcement learning

GRF academy_counterattack_hard (4v3)

69Mean Win Rate

10

Multi-agent reinforcement learning

GRF cthard 4v3

0.89Reward

10

State Entropy Estimation

GRF (3v1)

0.012State Entropy

7

Multi-Agent Reinforcement Learning

GRF 3v1 hard

94Win Rate

7

Strategy Discovery

GRF (corner)

3Distinct Strategies

6

Strategy Discovery

GRF (CA)

3.3Distinct Strategies

6

State Entropy Estimation

GRF (CA)

0.039State Entropy

5

State Entropy Estimation

GRF (Corner)

0.031State Entropy

4

Multi-agent Reinforcement Learning

GRF CA(hard)

77.38Success Rate

4

Multi-agent Reinforcement Learning

GRF 3v.1

88.03Success Rate

4

Multi-agent Reinforcement Learning

GRF PS

94.92Success Rate

3

State Entropy Estimation

GRF Corner (test)

—Primary metric

0

State Entropy Estimation

GRF CA (test)

—Primary metric

0

State Entropy Estimation

GRF 3v1 (test)

—Primary metric

0