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

Reinforcement Learning on BipedalWalker

314.24Average Episode Reward

TD3

-127.7704-13.0177101.735216.4877Nov 2, 2023Jan 20, 2024Apr 9, 2024Jun 27, 2024Sep 15, 2024Dec 3, 2024Feb 21, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2023.11
314.24-
2023.11
312.14-
2023.11
311.78-
2025.02
310.2-
2023.11
309.57-
2023.11
309.43-
2023.11
308.31-
2025.02
307.3-
2023.11
291.79-
2023.11
287.43-
2025.02
286.2-
2025.02
280.9-
2025.02
280.4-
2025.02
264.4-
2025.02
262.6-
2025.02
241-
2025.02
235.1-
2023.11
209.42-
2025.02
94.2-
2023.11
-110.77-
2023.11
-1,000
2023.11
-400,000
2023.11
-2,000