arXiv (All)
open access
AReaL-TIK: Stateful Agentic Optimization of Unified RL Kernels through an Optimization IR
Reinforcement learning (RL) post-training often uses distinct GPU kernels for rollout and policy update. In synchronous PPO and GRPO, numerical disagreement can perturb ratios between current token probabilities and those assigned during rollout. Recomputing rollout log-probabilities with the policy
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- AReaL-TIK: Stateful Agentic Optimization of Unified RL Kernels through an Optimization IR#1108701
- RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards#175247
- Optimization Algorithms#359805
- Nonlinear Optimization#67412
- Bellman-Certified Rounding for Sparse Policy Deployment in MDPs#1154948
Record · ID 1129739
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive