Home Knowledge Base Safe RL

Safe RL

No mentions found

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

Related Articles from SNS

Interaction-Limited Safe Continuous-Time RL for Dynamical Medical Treatment

arXiv:2606.01051v1 Announce Type: new Abstract: Dynamic medical treatment requires deciding treatment intensity and intervention timing, while patient states evolve continuously and adverse events may occur between clinical interactions. Most existing treatment learning methods assume fixed schedules or enforce safety only at discrete decision points. We propose Interaction-Limited Safe Continuous-Time Reinforcement Learning, a framework that jointly optimizes treatment administration and...

arXiv CS 9d ago

Safe-RULE: Safe Reinforcement UnLEarning

arXiv:2606.09559v1 Announce Type: new Abstract: Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such as robotics systems. However, its reliance on static datasets exposes offline Safe RL to data poisoning attacks, where adversaries inject malicious samples that compromise safety and induce unsafe policy behavior. In this work, we propose a new learning paradigm, named safe reinforcement...

arXiv CS 2d ago

Easy-to-Use Shielding for Reinforcement Learning

Announce Type: new Abstract: Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their environment. Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their environment. Shielding is one such technique that assumes domain knowledge in the form of an environment model to decide upon action safety.

arXiv CS 8d ago

Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learning

arXiv:2605.26452v2 Announce Type: replace Abstract: Safe reinforcement learning (RL) for robotic systems requires policies that improve task performance while satisfying state and input constraints during both training and deployment. Control barrier functions (CBFs) provide a principled mechanism for enforcing forward invariance through minimally invasive safety filters, but their use in model-free RL is limited by the need for accurate dynamics and hand-designed barrier certificates. We...

arXiv CS 2d ago

Value Flows

arXiv:2510.07650v4 Announce Type: replace Abstract: While most reinforcement learning methods today flatten the distribution of future returns to a single scalar value, distributional RL methods exploit the return distribution to provide stronger learning signals and to enable applications in exploration and safe RL. While the predominant method for estimating the return distribution is by modeling it as a categorical distribution over discrete bins or estimating a finite number of...

arXiv CS 9d ago

A Systematic Investigation of RL-Jailbreaking in LLMs

Announce Type: replace Abstract: The evolution of generative models from next-token predictors to autonomous engines of complex systems necessitates rigorous safety hardening. Adversarial jailbreaking, the strategic manipulation of models to elicit harmful output, remains a primary threat to safe deployment. While Reinforcement Learning (RL) frames jailbreaking as a multi-step attack through sequential optimization, a mechanistic understanding of why the framework succeeds remains incomplete.

arXiv CS 7d ago

Explainably Safe Reinforcement Learning

Announce Type: new Abstract: Trust in a decision-making system requires both safety guarantees and the ability to interpret and understand its behavior. This is particularly important for learned systems, whose decision-making processes are often highly opaque. Shielding is a prominent model-based technique for enforcing safety in reinforcement learning.

arXiv CS 7d ago

HALO: Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization

Announce Type: replace Abstract: To improve generalization and resilience in human-robot collaboration (HRC), robots must contend with diverse combinations of human behaviors and contexts, motivating multi-agent reinforcement learning (MARL). However, inherent heterogeneity between robots and humans creates a rationality gap (RG), where decentralized policy updates deviate from cooperative joint optimization. The resulting learning problem is a general-sum differentiable game, so independent...

arXiv CS 9d ago

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning

Announce Type: new Abstract: As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents unsafe capabilities and underscores the risk of power-seeking. While broad action space and greater environment influence are essential for task fulfillment, they create a fragile risk surface where minor errors or hallucinations are magnified into catastrophic failures. In response, we...

arXiv CS 9d ago

Scenario Generation for Risk-Aware Reinforcement Learning with Probably Approximately Safe Guarantees

Announce Type: replace Abstract: Guaranteeing safety is critical to the deployment of reinforcement learning (RL) agents in the real-world, especially as policies learned using deep RL may demonstrate susceptibility to transition perturbations that result in unknown or unsafe behaviour. A method of policy verification is to construct probabilistic barrier-certificates by sampling policy trajectories with respect to safety constraints, thereby demarcating known safe behaviour from unknown...

arXiv CS 3d ago