Skip to main content

Point-Mass REDQ Baseline results

Created on December 17|Last edited on December 17

Sparse rewards


5001k1.5kepisode0100200300400500
displayName: redq_point_mass_sparse_no_early_termination
Run set
2

Step 5000:

Step 15k:


Step 30k



Step 100k




Run set
2

Step 5k


Step 15k:


Step 30k:




Distance-to-goal with tolerance

Reminder: this reward function is always positive, and goes from 0 (when distance \in (initial_distance, \infty)) to 1 (when distance \in [0, 0.05))

Run set
2

Step 5k:

Step 15k:


Step 30k:


Step 100k: