arXiv:2606. 09559v1 Announce Type: cross Abstract: Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such as robotics systems.
arXiv:2606. 09499v1 Announce Type: cross Abstract: World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training data or simulating real world environments, with many works proposing their integration into the robot learning pipeline.
arXiv:2606. 31320v1 Announce Type: new Abstract: Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics.
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.
arXiv:2508. 20697v4 Announce Type: replace Abstract: As large language models (LLMs) continue to grow in capability, so do the risks of harmful misuse through fine-tuning.
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.
The paper introduces new evaluation metrics for safe reinforcement learning that go beyond average safety guarantees by examining how often and how severely safety bounds are violated, consistency across tasks and bounds, and the relationship between training-time and final policy behavior. It also proposes a safety tier system for categorizing algorithms and presents empirical safety evaluations on multiple navigation tasks. The authors recommend reporting aggregate metrics, distributional data, and task‑specific results together, and provide an open‑source suite, SafeRLEval, to facilitate reliable safety assessment.
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.
arXiv:2602. 04899v2 Announce Type: replace-cross Abstract: We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out.
arXiv:2506. 06891v3 Announce Type: replace Abstract: We study the corruption-robustness of in-context reinforcement learning (ICRL), focusing on the Decision-Pretrained Transformer (DPT, Lee et al.
arXiv:2606. 29867v1 Announce Type: cross Abstract: Deep Reinforcement Learning (DRL) has achieved significant success in robotics and autonomous systems, yet remains vulnerable to adversarial perturbations that can severely degrade performance.
arXiv:2607. 07252v1 Announce Type: new Abstract: Reinforcement learning (RL) enables the synthesis of control policies directly from data, making it highly appealing for complex cyber-physical systems (CPSs) and robotics.
arXiv:2604. 10062v3 Announce Type: replace Abstract: We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target RL agent to adopt a policy that aligns with the attacker's objectives.