Select runs that logged test_score
to visualize data in this line chart.
to visualize data in this line chart.
Updated Mountain Car Offline Experiments
Using Updated Implementation and 3,000,000 Iterations.
Created on February 8|Last edited on February 14
Comment
Comparing training performance with and without human actions:
-2 Penalty, 3,000,000 Iterations, over 5 Seeds Each (with and without human actions)
Run set
0
-1 Penalty, 3,000,000 Iterations, over 5 Seeds Each (with and without human actions)
Run set
0
Add a comment