…advantage-weighted quadratic regularizer on policy shift . DRPO preserves the same trust-region geometry as DPPO while inducing bounded, continuous gradient weights that attenuate diverging updates and provide corrective signals beyond the…
…The method is fully compatible with standard policy optimization and requires neither an additional critic nor extra rollouts. We evaluate AgentOPSD on ALFWorld , WebShop , and Search-QA using Qwen2.5 models at…
…Among existing recipes, group-based policy gradient is prevalent, which samples a group of responses per prompt and updates the policy via group-relative advantage signals. This work reveals that these optimization…
…Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling Published on Jun 8 Submitted by haoran xu on Jun 12 Authors: , , , Jiaze Li , , Abstract Sign-Gated On-Policy…
…To break free from these constraints, we propose Unbounded Positive Asymmetric Optimization (UP), a universal and plug-and-play objective. UP theoretically restructures the optimization process by anchoring the policy to its…
…Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning (2026) Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes (2026) Self-Induced Outcome Potential: Turn-Level Credit Assignment…
…Adding a new task to a VLA policy usually means collecting teleop demos and fine-tuning per task. We replace that target-side cost with retrieval: train the policy once, freeze it…
…In closed-loop simulation , the driving policy model actively interacts with the environment, where its actions dynamically update the simulator state and directly influence the next set of generated sensor observations. While…
…trajectory depth, and a fixed clipping range governs policy updates identically for turns with vastly different IG signals. In this paper, we propose A^2TGPO (Agentic Turn-Group Policy Optimization with Adaptive…
…Yet many real-world scenarios are inherently dynamic, such as audio and video stream, where information arrives as a continuous stream and models must reason, update, and respond under partial observations. Recent…