Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-agent Reinforcement Learning on Boxpushing
Loading...
145.35
Reward
Ours
2.922
39.8985
76.875
113.8515
Aug 16, 2023
Reward
Updated 1mo ago
Evaluation Results
Method
Method
Links
Reward
Ours
Horizon=7
2023.08
145.35
FM-E
Horizon=7
2023.08
138.44
RNN-E
Horizon=7
2023.08
132.7
Ours
Horizon=6
2023.08
98.76
Ours
Horizon=5
2023.08
98.73
FM-E
Horizon=5
2023.08
96.4
FM-E
Horizon=6
2023.08
94.61
RNN-E
Horizon=6
2023.08
94.36
Ours
Horizon=4
2023.08
81.44
FM-E
Horizon=4
2023.08
77.8
FM-E
Horizon=3
2023.08
64.22
Ours
Horizon=3
2023.08
62.78
RNN-E
Horizon=5
2023.08
21.78
RNN-E
Horizon=4
2023.08
9.1
RNN-E
Horizon=3
2023.08
8.4
Feedback
Search any
task
Search any
task
