EnvSched schedules agent RL rollouts by environment and task
On Qwen3-8B it scores 48.81 after 40 steps, above random selection's best score after 120 steps.
1 stories, newest first · one card per story
On Qwen3-8B it scores 48.81 after 40 steps, above random selection's best score after 120 steps.
Today 669 readers · 816 views · 616 reads · all time 158K views