-
Notifications
You must be signed in to change notification settings - Fork 581
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
How to run PPO for agents?
questionFurther information is requestedFurther information is requestedStatus: Open.#704 In rllm-org/rllm;- Status: Open.#655 In rllm-org/rllm;
Example for training on SWE (agentic software-engineering) tasks?
questionFurther information is requestedFurther information is requestedStatus: Open.#625 In rllm-org/rllm;AgentWorkflowPPOTrainer: GRPO groups by trajectory.uid instead of prompt/agent key
questionFurther information is requestedFurther information is requestedStatus: Open.#605 In rllm-org/rllm;- Status: Open.#468 In rllm-org/rllm;
- Status: Open.#465 In rllm-org/rllm;
Qwen3-VL training with flashattn+vllm
questionFurther information is requestedFurther information is requestedStatus: Open.#464 In rllm-org/rllm;Add Daytona as a code execution sandbox backend
enhancementNew feature or requestNew feature or requestStatus: Open.#459 In rllm-org/rllm;Qwen3.5 support
questionFurther information is requestedFurther information is requestedStatus: Open.#434 In rllm-org/rllm;context compression
questionFurther information is requestedFurther information is requestedStatus: Open.#432 In rllm-org/rllm;- Status: Open.#391 In rllm-org/rllm;
- Status: Open.#388 In rllm-org/rllm;