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

Offline Reinforcement Learning on D4RL Gym hopper (medium-replay)

105.6Normalized Return

BRAC

4.230.52556.8583.175Oct 1, 2021Jun 27, 2022Mar 23, 2023Dec 17, 2023Sep 11, 2024Jun 7, 2025Mar 4, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2021.10
105.6
2024.01
104.9
2026.03
103.2
2022.06
102.9
2022.06
102.8
2022.06
102.8
2025.11
102.7
2026.03
102.1
2021.10
101.8
2024.01
101.8
2025.11
101.1
2021.10
101
2022.06
101
2024.01
101
2025.11
100.7
2022.06
100.6
2026.03
100
2021.10
98.1
2021.10
97
2026.03
95
2025.11
95
2026.03
94.7
2025.11
94.7
2021.10
93.6
2026.03
89
2021.10
86.3
2022.06
86.3
2021.10
84
2026.03
83.3
2026.03
82.7
2021.10
81.3
2025.11
60.9
2021.10
54.8
2021.10
54
2026.03
52.1
2021.10
48.6
2024.01
48.6
2021.10
46.6
2021.10
41.1
2021.10
19.7
2025.11
18.1
2022.06
16.6
2024.01
16.6
2021.10
8.1