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

Coinrun

Benchmarks

Task NameDataset NameSOTA ResultTrend
Continual Reinforcement LearningCoinRun Normalized Continual Learning
Max Performance1.34
9
Reinforcement LearningCoinrun (test)
Avg Cumulative Reward9.4
5
Continual Reinforcement LearningCoinRun Two-cycle (train)
C1 Final Score0.521
3
Continual Reinforcement LearningCoinRun Reversed task order
Forgetting-0.029
3
Continual Reinforcement LearningCoinRun
Forgetting-0.012
3
Showing 5 of 5 rows