Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Continuous Control on BipedalWalker v3
Loading...
276.98
Episodic Cumulative Reward
AOC-BC
-127.5072
-22.4961
82.515
187.5261
Oct 11, 2023
Episodic Cumulative Reward
Updated 4d ago
Evaluation Results
Method
Method
Links
Episodic Cumulative Reward
AOC-BC
sampler=Behavior Clone...
2023.10
276.98
BC
training_data=offline...
2023.10
208.72
Data-Avg-Return
2023.10
202.25
MFRL
type=model-free RL
2023.10
18.51
AOC-Uniform
sampler=uniform sampler
2023.10
-90.44
MPC
type=model-based RL
2023.10
-96.82
KNN
variant=k-neighbors
2023.10
-109.72
1NN
variant=nearest-neighbor
2023.10
-111.95
Feedback
Search any
task
Search any
task