fix: custom reward function dependent on env reward + extensions

2026-04-17 14:23:57 +02:00 · 2026-04-17 14:23:57 +02:00 · ad17401c4c
commit ad17401c4c
parent 3efee5d746
9 changed files with 71 additions and 50 deletions
--- a/configs/ppo/debug.yaml
+++ b/configs/ppo/debug.yaml
@ -1,5 +1,5 @@
 learning_rate: 0.0003
-total_timesteps: 409600 
+total_timesteps: 409600
 num_envs: 32
 num_steps: 32
 anneal_lr: true