Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Goal-navigation on Two Rooms custom (Room 1)
Loading...
-11
Return
Random
-11.55
-11.275
-11
-10.725
Jun 19, 2026
Return
Updated 1mo ago
Evaluation Results
Method
Method
Links
Return
Random
Algorithm=CQL, Trainin...
2026.06
-11
APT
Algorithm=CQL, Trainin...
2026.06
-11
SMM
Algorithm=CQL, Trainin...
2026.06
-11
CIC
Algorithm=CQL, Trainin...
2026.06
-11
RND
Algorithm=CQL, Trainin...
2026.06
-11
ROVER
Algorithm=CQL, Trainin...
2026.06
-11
Random
Algorithm=DDPG, Traini...
2026.06
-11
APT
Algorithm=DDPG, Traini...
2026.06
-11
SMM
Algorithm=DDPG, Traini...
2026.06
-11
CIC
Algorithm=DDPG, Traini...
2026.06
-11
RND
Algorithm=DDPG, Traini...
2026.06
-11
ROVER
Algorithm=DDPG, Traini...
2026.06
-11
DDPG (online)
Training protocol=50k...
2026.06
-11
Feedback
Search any
task
Search any
task