14 tagged agentic rl, measured the same way as everything else here.
Browse within: Distributed Training 14GRPO 14Multi-Agent 14Multimodal 14Post-Training 14
Skill Claude CodeCodex
A troubleshooting workflow for Ray, a system that runs machine-learning jobs across multiple computers or GPUs, when a distributed training job stops making progress.
Skill Claude CodeCodex
Integrate a new NVIDIA NeMo Gym environment into Relax as a three-step recipe. Use when adding or debugging a recipe under examples/nemogymagentic/recipes; covers data preparation, a local private Gym service, direct Ray training launch, verifier validation, callback networking, lifecycle cleanup, and failure triage.
Skill Claude CodeCodex
Migrate RL training recipes from verl to Relax framework. Use when user wants to port reward functions, tool environments, training scripts, or any recipe code from the verl (volcengine/verl) codebase to Relax. Handles reward, rollout, tool/env, dataset, and launch script conversion. Supports both colocate (default)…