Bargaining Game
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Bargaining Game 2000 trajectories, pi^U behavior policy
1.4Regret
12
Bargaining Game 2000 trajectories sigma^eq behavior policy
0.64Regret
12
Bargaining Game 1000 trajectories, pi^U behavior policy
2.12Regret
12
Bargaining Game 1000 trajectories, sigma^eq behavior policy
1.01Regret
12
Bargaining Game 500 trajectories, pi^U behavior policy
3.76Regret
12
Bargaining Game 500 trajectories, sigma^eq behavior policy
1.96Regret
12