Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Reinforcement Learning on D4RL Gym (medium-replay, medium-expert)
Loading...
45.7
HalfCheetah (medium-replay)
CQL
26.356
31.378
36.4
41.422
Jan 30, 2023
HalfCheetah (medium-replay)
Hopper (medium-replay)
Walker (medium-replay)
HalfCheetah (medium-expert)
Hopper (medium-expert)
Walker2d (medium-expert)
Average Return
Updated 3mo ago
Evaluation Results
Method
Method
Links
HalfCheetah (medium-replay)
Hopper (medium-replay)
Walker (medium-replay)
HalfCheetah (medium-expert)
Hopper (medium-expert)
Walker2d (medium-expert)
Average Return
CQL
Learning Source=Task r...
2023.01
45.7
84.1
80
88.5
103.7
108.4
85.1
IQL
Learning Source=Task r...
2023.01
44.3
100.5
74.8
85.2
84.1
107.5
82.7
PT+IQL
Learning Source=Prefer...
2023.01
42.3
59.7
43.3
83.6
67.8
109.8
67.8
DPPO
Learning Source=Prefer...
2023.01
40.8
73.2
50.9
92.6
107.2
108.6
78.8
PT+CQL
Learning Source=Prefer...
2023.01
27.1
49.1
52.8
77.1
89.2
77.7
62.2
Feedback
Search any
task
Search any
task
