Forwarding from the Atropos GitHub:
‘Hey! Nous Research here - we’re the authors of an LLM RL environments repo called Atropos which is designed to provide rollouts for multi-environment runs, and where each individual env can be single-turn, multi-turn, or multi-agent, R1-zero style, or have a custom chat template. Furthermore, environments can define token-level advantages and so are not necessarily tied to the same RL training algorithm’
Full description of the bounty here: Atropos integration ($2500 bounty) · Issue #1782 · volcengine/verl · GitHub