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

Reinforcement Learning on Seaquest

5,000Average Reward

Average Human

3,356.83,783.44,2104,636.6May 29, 2024
Updated 3mo ago

Evaluation Results

MethodLinks
5,000
2024.05
3,600
2024.05
3,500
2024.05
3,420