Home Knowledge Base Dynamic sAmpling Policy Optimization

Dynamic sAmpling Policy Optimization

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

L-SDPPO: Policy Optimization of Spiking Diffusion Policy for Intra-vehicular Robotic Manipulation

arXiv:2606.06049v1 Announce Type: new Abstract: Intra-vehicular robots in spacecraft help reduce astronaut workload and improve mission efficiency. Recent research focuses on using deep learning methods to achieve the acute control required for operations in these complex environments. However, objects exhibit unpredictable, unconstrained drift without gravitational damping.

arXiv CS 5d ago

Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief

arXiv:2606.00680v2 Announce Type: replace Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets. A bottleneck of this paradigm is managing epistemic uncertainty, which arises from limited data coverage (sample-level) and the ambiguity in identifying transition dynamics from finite data (model-level). To provide a unified quantification of these uncertainties, Bayesian RL has been proposed by treating the dynamics model as a random variable and...

arXiv CS 7d ago

TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization

Announce Type: new Abstract: Latent reasoning has emerged as a promising alternative to discrete Chain-of-Thought (CoT) in large language models (LLMs), enabling more expressive reasoning by operating over continuous representations. However, the inherently deterministic nature of continuous representations limits policy exploration in reinforcement learning (RL). To address this, we propose TARPO (Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization), a pure RL...

arXiv CS 5d ago

The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning

arXiv:2606.07950v1 Announce Type: new Abstract: RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often treats easy, hard, and learnable questions alike through uniform sampling and weighting, leading to inefficient compute allocation. We study GRPO by tracking token log-probabilities, group-normalized advantages, and the induced token-level update weights. This reveals three recurring dynamics as training proceeds: (1) confidence inflation,...

arXiv CS 1d ago

Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification

Announce Type: replace Abstract: Many inference-time language-model pipelines combine a cheap reward signal with an expensive verifier, such as exact answer checking in mathematical reasoning or hidden-test execution in code generation. We formalize this setting using a learning-theoretic lens as generative active search: a cost-sensitive first-positive search problem in which a policy adaptively samples candidates from an unknown distribution, observes cheap scores, and pays for verifier...

arXiv CS 1d ago

Shield-Loco: Shielding Locomotion Policies with Predictive Safety Filtering

arXiv:2606.07193v1 Announce Type: new Abstract: Reinforcement learning (RL) policies enable dynamic legged locomotion but lack mechanisms to avoid violations of safety constraints that are absent during training. Large-scale offline safe learning is impractical for covering all edge cases. Existing safety frameworks either rely on reduced-order models that cannot reason about whole-body behaviors or require conservative recovery controllers that degrade task performance.

arXiv CS 2d ago

Unlocking Proactivity in Task-Oriented Dialogue

arXiv:2605.22240v2 Announce Type: replace Abstract: Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that actively probes the user's concerns and steers the conversation toward acceptance within a bounded number of turns. Yet post-trained LLMs are inherently conservative, and reward-shaping RL (e.g., GRPO) struggles since it only re-weights what an already passive policy samples. We show that conditioning on the user's latent concerns unlocks...

arXiv CS 6d ago

Generative Reasoning Re-ranker

arXiv:2602.07774v5 Announce Type: replace Abstract: Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge. However, existing work has three key limitations: (1) most efforts focus on retrieval and ranking, while the reranking phase, critical for refining final recommendations, is largely overlooked; (2) LLMs are typically used in zero-shot or supervised fine-tuning settings, leaving their...

arXiv CS 1d ago

AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO

Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has demonstrated remarkable success in aligning text-to-image (T2I) flow models with human preferences. However, we have identified that the learning loop of current flow-based GRPO is fundamentally decoupled from the learner's current capability, suffering from critical blind spots at both prompt selection and advantage estimation: (i) Existing methods sample prompts randomly, overlooking the substantial impact of data...

arXiv CS 2d ago

Retry Policy Gradients in Continuous Action Spaces

arXiv:2606.05888v1 Announce Type: new Abstract: Retry-based objectives such as pass@K and max@K optimize the best return obtained from multiple sampled trajectories, and recent work has shown that they can promote exploration without explicit exploration bonuses. In discrete action spaces, ReMax was shown to do so by adapting to return uncertainty. In this work, we introduce pathwise derivative estimators for retry objectives and use them to extend ReMax to continuous action spaces.

arXiv CS 5d ago