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

Offline Meta-Reinforcement Learning on Walker-Rand-Params sampled 10 unseen (test)

344.2Average Return

CSRO

241.864268.432295321.568Nov 7, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.11
344.2
2023.11
319.7
2023.11
312.5
2023.11
284.5
2023.11
275.2
2023.11
262
2023.11
260.6
2023.11
253.3
2023.11
247.5
2023.11
245.8