online training works (loss goes down), remove repeat_action, eval_policy outputs episodes data, eval_policy uses max_episodes_rendered

2026-07-25 18:56:09 +00:00 · 2024-04-10 11:34:01 +00:00
parent 19e7661b8d
commit 06573d7f67
11 changed files with 219 additions and 211 deletions
@@ -36,6 +36,7 @@ policy:
  log_std_max: 2

  # learning
+  batch_size: 256
  max_buffer_size: 10000
  horizon: 5
  reward_coef: 0.5