Success Visitation Matching transforms sparse RL rewards into dense process rewards
A new arXiv paper proposes a method to convert sparse outcome rewards into dense process rewards by training a discriminator to distinguish successful from unsuccessful episodes and using it to guide policy learning toward the state-action visitations of successful trajectories. The approach is proven to preserve the optimal policy while providing denser feedback on task progress. Experiments focus on robotic manipulation finetuning in both simulated and real-world settings, showing faster RL convergence than sparse-reward baselines.
Related guides (2)
Related events (8)
ACPO: Adaptive Clip Policy Optimization improves RLVR training for LLM reasoning
A new arXiv preprint provides theoretical analysis of Reinforcement Learning from Verifiable Rewards (RLVR) updates, identifying off-policy degree and gradient expectation as key factors governing update dynamics. The authors show that differences in gradient steps per rollout substantially affect importance sampling ratio distributions and which tokens dominate updates. Based on this analysis, they propose Adaptive Clip Policy Optimization (ACPO), which adjusts clipping boundaries per token group by empirical variance of importance sampling ratios, outperforming DAPO and CISPO baselines on 3B and 7B models across math, tabular QA, and logic benchmarks.
Agency-transferring technique improves RL policy training by bootstrapping from baseline policies
A new arXiv paper proposes a model-free reinforcement learning method that embeds an existing suboptimal baseline policy into training via an arbitration mechanism, progressively transferring control from the baseline to a trainable neural network. The approach yields high goal-reaching rates from the start of training and produces a standalone policy that outperforms the baseline without requiring it at inference time. Theoretical bounds on goal-reaching probability are derived, and empirical results on continuous-control benchmarks show competitive or superior returns compared to existing methods.
STARE: Token-level advantage reweighting to prevent entropy collapse in GRPO-style RL training
Researchers introduce STARE, a method addressing policy entropy collapse in GRPO-style reinforcement learning from verifiable rewards (RLVR) for LLM post-training. Through first-order gradient analysis, they identify a token-level credit assignment mismatch and propose selectively reweighting advantages for entropy-critical tokens using batch-internal surprisal quantiles plus a closed-loop entropy gate. Evaluated across 1.5B–32B models on short/long chain-of-thought and multi-turn tool use tasks, STARE outperforms DAPO and other baselines by 4–8% on AIME24/25 while sustaining stable training over thousands of steps.
HABC: Hierarchical Advantage Weighting for Online RL Fine-Tuning of Vision-Language-Action Policies
Researchers introduce Hierarchical Advantage-Weighted Behavior Cloning (HABC), a method for fine-tuning pretrained Vision-Language-Action (VLA) policies via online RL using only sparse binary episode outcomes. HABC trains separate critic heads for viability and efficiency objectives, combines them via a state-adaptive gate, and applies intervention-aware credit assignment to avoid incorrect supervision across human-intervention boundaries. On three contact-rich bimanual real-robot tasks, HABC improves success rates from SFT baselines of 36%, 44%, and 12% to 92%, 88%, and 38% respectively. The work addresses a fundamental credit assignment problem in robot learning from sparse outcome signals.
In-Context Reward Adaptation for Robust Preference Modeling
This paper proposes In-Context Reward Adaptation (ICRA), a transformer-based framework that infers reward structures from small sets of preference demonstrations at inference time, without retraining. The key finding is that standard transformers exhibit asymptotic bias toward ground-truth rewards, but incorporating human response time as an auxiliary signal resolves this limitation and enables generalization to unseen preference domains. The approach addresses a core limitation of static RLHF reward models, which fail to handle heterogeneous or shifting human value distributions.
POW3R: Policy-Aware Rubric Rewards for More Efficient RLVR Training
This paper identifies a failure mode in rubric-based reinforcement learning with verifiable rewards (RLVR): static aggregation of criterion weights conflates human-assigned importance with current optimization utility, causing many criteria to be either already saturated or unreachable. The authors introduce POW3R, a framework that dynamically reweights criterion-level rewards during training using rollout-level contrast to emphasize criteria that currently differentiate policy outputs. Across three base policies and two datasets (multimodal and text-only), POW3R wins 24 of 30 comparisons on rubric reward and strict completion metrics, and reaches equivalent performance in 2.5–4× fewer training steps than vanilla GRPO with rubric rewards.
VEPO: Vision-anchored token selection improves RL for visual reasoning
A new arXiv paper identifies a failure mode of entropy-based credit assignment in multimodal reinforcement learning: vision-sensitive tokens with naturally low entropy are systematically ignored, causing the mechanism to collapse in visual reasoning tasks. The authors propose VEPO (Vision-Entropy token-selection for Policy Optimization), which couples visual sensitivity with token entropy via a multiplicative scheme to redirect gradient credit toward tokens that are both visually grounded and semantically informative. VEPO outperforms entropy-only baselines by 2.28 points at 7B scale and 3.15 points at 3B scale on visual reasoning benchmarks.
DRPO: Smooth divergence regularization replaces hard masking in LLM RL training
A new arXiv preprint proposes Divergence Regularized Policy Optimization (DRPO), a method that replaces the hard trust-region mask used in DPPO with a smooth advantage-weighted quadratic regularizer on policy shift. The approach addresses a known weakness in PPO and GRPO where importance ratios poorly proxy distributional shift in long-tailed vocabularies, and in DPPO where gradient signals are discarded rather than corrected at trust-region boundaries. Experiments across model scales, architectures, and precision settings show improved stability and efficiency in LLM RL post-training.