SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration

Safe Exploration via Policy Priors

arXiv:2601. 19612v3 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.

Benchmarking safe exploration in deep reinforcement learning

RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards

RePolicy is a reinforcement learning approach designed to invoke safety policies for language model agents by evaluating entire execution trajectories within context-dependent policy libraries. It generates policy-grounded rationales and safety judgments, and is initialized with the PolicyTraj-20K dataset before fine-tuning via GRPO with verifiable rewards and policy-context perturbation. Experiments on six safety benchmarks demonstrate strong safety-detection performance and robust policy invocation across varying contexts.

Safe Meta-Reinforcement Learning via Information Space Reachability

arXiv:2609.15915v1 Announce Type: new Abstract: Meta-reinforcement learning (meta-RL) enables agents to adapt to unseen tasks with limited experience. Despite its promise, the application of meta-RL...

Directional Constraints for Efficient Exploration in Safe Reinforcement Learning

arXiv:2607. 12784v1 Announce Type: cross Abstract: Reinforcement Learning has revolutionized the landscape of robotic research, allowing robust learning of complex robotic skills in simulation.

Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning

arXiv:2606. 06976v1 Announce Type: new Abstract: Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct responses, which may accumulate errors throughout multi-step interactions.

Safe Online Learning via Smooth Safety-Structured Policy Composition

arXiv:2606. 31320v1 Announce Type: new Abstract: Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics.

RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards

Safeguarding language model agents requires assessing complete execution trajectories under context-dependent safety policies. Existing policy-aware safeguards mainly rely on prompting or supervised f...

Directional Constraints for Efficient Exploration in Safe Reinforcement Learning

Reinforcement Learning has revolutionized the landscape of robotic research, allowing robust learning of complex robotic skills in simulation. However, real-world deployment in open-ended environments requires strong safety guarantees to prevent dangerous or harmful behaviors.

Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning

The paper introduces Safety to Competence (S2C), a two‑stage reinforcement learning framework that first learns a safety filter and then trains a competitive task policy while embedding the filter. By separating safety synthesis from task learning, S2C reduces training complexity and prevents the policy from being exploited by adversarial attacks. Experiments on simulated touchdown games show that S2C achieves higher win rates, better Elo ratings, and lower exploitability than eight safe‑RL baselines, and hardware tests confirm its competence against a human opponent.

Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making

The paper introduces RATTL (Risk-Adversarial Total-Reward Learning), a framework that adjusts an agent’s caution based on epistemic uncertainty by using a Bayesian posterior over dynamics and a Wasserstein ambiguity set whose radius depends on that posterior. As evidence accumulates, the radius shrinks, smoothly transitioning the agent’s behavior from worst-case robustness to risk-neutral reward maximization. The authors prove a Safety Sandwich theorem showing RATTL’s value lies between the uninformed robust value and the full-knowledge optimum, and demonstrate the method on a binary-hazard example where the criterion reduces to Conditional Value-at-Risk.

Threat-guided Policy-aware Scene Perturbation for Safe Autonomous Driving with Online Reinforcement Learning

arXiv:2608. 10403v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown promising performance in autonomous driving, yet ensuring the safety of online RL policies remains challenging due to insufficient exposure to safety-critical driving scenes.