Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Online Reinforcement Learning on Antmaze umaze-diverse
Loading...
99.9
Score
BC-PEX
-3.996
22.977
49.95
76.923
Oct 28, 2023
Score
Updated 3mo ago
Evaluation Results
Method
Method
Links
Score
BC-PEX
Environment Steps=500k
2023.10
99.9
RLPD
Reward Setting=with tr...
2023.10
99.9
UBER
Environment Steps=500k
2023.10
98.8
BC-PEX
Environment Steps=100k
2023.10
95.5
UBER
Environment Steps=100k
2023.10
94.5
RLPD
Reward Setting=with tr...
2023.10
83.3
RLPD
Reward Setting=without...
2023.10
0
RLPD
Reward Setting=without...
2023.10
0
Feedback
Search any
task
Search any
task
