Kernel-Based Safe Exploration in Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2605.22207v1
• Date: Thu, 21 May 2026 09:12:44 GMT
• Title: Kernel-Based Safe Exploration in Deep Reinforcement Learning
• Abstract summary: A barrier is a function from states to reals that assigns low values to the initial states, high values to the unsafe states, and decreases in expectation on each transition.<n>Previous attempts learned a barrier function directly from exploration data, but this required either large amounts of data or restrictions on the system dynamics.<n>We show how kernel embeddings can be used to learn barrier functions during deep reinforcement learning for systems with unknown dynamics.
• Score: 8.876276636425402
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safety has been a major concern when deploying deep reinforcement learning algorithms in the real world. A promising direction that ensures that the learned policy does not visit unsafe regions is to learn a \emph{barrier function} along with the policy. A barrier is a function from states to reals that assigns low values to the initial states, high values to the unsafe states, and decreases in expectation on each transition; such a function can be used to bound the probability of reaching unsafe states. Previous attempts learned a barrier function directly from exploration data, but this required either large amounts of data or restrictions on the system dynamics. In this paper, we show how kernel embeddings can be used to learn barrier functions during deep reinforcement learning for stochastic systems with unknown dynamics. Our algorithm, \emph{kernel-based safe exploration (KBSE)}, learns an optimal policy and a barrier simultaneously during exploration. The barriers are computed iteratively, represented as conditional mean embeddings, and provide better probabilistic safety guarantees with more exploration. The exploration algorithm uses the learned barrier functions to identify safety violations. In the case of violation, it intervenes to modify the unsafe action to a safe action, thereby ensuring that the exploration is restricted to actions that bound the probability of reaching unsafe states. We evaluate KBSE on several complex continuous control benchmarks. Experimental results establish our new algorithm to be suitable for synthesizing control policies that are probabilistically safe without degradation in reward accumulation.

Related papers

• Safe-Support Q-Learning: Learning without Unsafe Exploration [5.892169642535822]
  We propose a Q-learning-based safe RL framework that eliminates unsafe state visitation during training.<n>Under the assumption that the induced trajectories remain within the safe set, this policy enables sufficient exploration within the safe region without requiring near-optimality.<n> Experimental results demonstrate that the proposed method achieves stable learning and well-calibrated value estimates and yields safer behavior with comparable or better performance than existing baselines.
  arXiv  Detail & Related papers  (2026-04-28T08:43:39Z)
• Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis [63.532413807686524]
  This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL) We propose a new architecture that handles the trade-off between efficient progress and safety during exploration.
  arXiv  Detail & Related papers  (2023-12-18T16:09:43Z)
• Safe Deep Reinforcement Learning by Verifying Task-Level Properties [84.64203221849648]
  Cost functions are commonly employed in Safe Deep Reinforcement Learning (DRL) The cost is typically encoded as an indicator function due to the difficulty of quantifying the risk of policy decisions in the state space. In this paper, we investigate an alternative approach that uses domain knowledge to quantify the risk in the proximity of such states by defining a violation metric.
  arXiv  Detail & Related papers  (2023-02-20T15:24:06Z)
• Provable Safe Reinforcement Learning with Binary Feedback [62.257383728544006]
  We consider the problem of provable safe RL when given access to an offline oracle providing binary feedback on the safety of state, action pairs. We provide a novel meta algorithm, SABRE, which can be applied to any MDP setting given access to a blackbox PAC RL algorithm for that setting.
  arXiv  Detail & Related papers  (2022-10-26T05:37:51Z)
• Safe Reinforcement Learning by Imagining the Near Future [37.0376099401243]
  In this work, we focus on the setting where unsafe states can be avoided by planning ahead a short time into the future. We devise a model-based algorithm that heavily penalizes unsafe trajectories, and derive guarantees that our algorithm can avoid unsafe states under certain assumptions. Experiments demonstrate that our algorithm can achieve competitive rewards with fewer safety violations in several continuous control tasks.
  arXiv  Detail & Related papers  (2022-02-15T23:28:24Z)
• Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning [7.138691584246846]
  We propose the safe set actor-critic (SSAC) algorithm, which confines the policy update using safety-oriented energy functions. The safety index is designed to increase rapidly for potentially dangerous actions. We claim that we can learn the energy function in a model-free manner similar to learning a value function.
  arXiv  Detail & Related papers  (2021-11-25T07:24:30Z)
• Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations [64.39401322671803]
  This paper explores the possibility of safe RL algorithms with zero training-time safety violations. We propose an algorithm, Co-trained Barrier Certificate for Safe RL (CRABS), which iteratively learns barrier certificates, dynamics models, and policies.
  arXiv  Detail & Related papers  (2021-08-04T04:59:05Z)
• Learning to Act Safely with Limited Exposure and Almost Sure Certainty [1.0323063834827415]
  This paper aims to put forward the concept that learning to take safe actions in unknown environments, even with probability one guarantees, can be achieved without the need for exploratory trials. We first focus on the canonical multi-armed bandit problem and seek to study the intrinsic trade-offs of learning safety in the presence of uncertainty.
  arXiv  Detail & Related papers  (2021-05-18T18:05:12Z)
• Conservative Safety Critics for Exploration [120.73241848565449]
  We study the problem of safe exploration in reinforcement learning (RL) We learn a conservative safety estimate of environment states through a critic. We show that the proposed approach can achieve competitive task performance while incurring significantly lower catastrophic failure rates.
  arXiv  Detail & Related papers  (2020-10-27T17:54:25Z)
• Provably Safe PAC-MDP Exploration Using Analogies [87.41775218021044]
  Key challenge in applying reinforcement learning to safety-critical domains is understanding how to balance exploration and safety. We propose Analogous Safe-state Exploration (ASE), an algorithm for provably safe exploration in MDPs with unknown, dynamics. Our method exploits analogies between state-action pairs to safely learn a near-optimal policy in a PAC-MDP sense.
  arXiv  Detail & Related papers  (2020-07-07T15:50:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.