An official website of the United States government
Among approaches for provably safe reinforcement learning, Model Predictive Shielding (MPS) has proven effective at complex tasks in continuous, high-dimensional state spaces, by leveraging a backup policy to ensure safety when the learned policy attempts to take risky actions. However, while MPS can ensure safety both during and after training, it often hinders task progress due to the conservative and task-oblivious nature of backup policies. This paper introduces Dynamic Model Predictive Shielding (DMPS), which optimizes reinforcement learning objectives while maintaining provable safety. DMPS employs a local planner to dynamically select safe recovery actions that maximize both short-term progress as well as long-term rewards. Crucially, the planner and the neural policy play a synergistic role in DMPS. When planning recovery actions for ensuring safety, the planner utilizes the neural policy to estimate long-term rewards, allowing it to observe beyond its short-term planning horizon. Conversely, the neural policy under training learns from the recovery plans proposed by the planner, converging to policies that are both high-performing and safe in practice. This approach guarantees safety during and after training, with bounded recovery regret that decreases exponentially with planning horizon depth. Experimental results demonstrate that DMPS converges to policies that rarely require shield interventions after training and achieve higher rewards compared to several state-of-the-art baselines
more »
« less
This content will become publicly available on June 4, 2026
Realizable Continuous-Space Shields for Safe Reinforcement Learning
While Deep Reinforcement Learning (DRL) has achieved remarkable success across various domains, it remains vulnerable to occasional catastrophic failures without additional safeguards. An effective solution to prevent these failures is to use a shield that validates and adjusts the agent’s actions to ensure compliance with a provided set of safety specifications. For real-world robotic domains, it is essential to define safety specifications over continuous state and action spaces to accurately account for system dynamics and compute new actions that minimally deviate from the agent’s original decision. In this paper, we present the first shielding approach specifically designed to ensure the satisfaction of safety requirements in continuous state and action spaces, making it suitable for practical robotic applications. Our method builds upon realizability, an essential property that confirms the shield will always be able to generate a safe action for any state in the environment. We formally prove that realizability can be verified for stateful shields, enabling the incorporation of non-Markovian safety requirements, such as loop avoidance. Finally, we demonstrate the effectiveness of our approach in ensuring safety without compromising the policy’s success rate by applying it to a navigation problem and a multi-agent particle environment1. Keywords: Shielding, Reinforcement Learning, Safety, Robotics
more »
« less
- Award ID(s):
- 2321786
- PAR ID:
- 10614736
- Publisher / Repository:
- 7th Annual Conference on Learning for Dynamics and Control
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In recent years, Deep Reinforcement Learning (DRL) has emerged as an effective approach to solving real-world tasks. However, despite their successes, DRL-based policies suffer from poor reliability, which limits their deployment in safety-critical domains. Various methods have been put forth to address this issue by providing formal safety guarantees. Two main approaches include shielding and verification. While shielding ensures the safe behavior of the policy by employing an external online component (i.e., a “shield”) that overrides potentially dangerous actions, this approach has a significant computational cost as the shield must be invoked at runtime to validate every decision. On the other hand, verification is an offline process that can identify policies that are unsafe, prior to their deployment, yet, without providing alternative actions when such a policy is deemed unsafe. In this work, we present verification-guided shielding — a novel approach that bridges the DRL reliability gap by integrating these two methods. Our approach combines both formal and probabilistic verification tools to partition the input domain into safe and unsafe regions. In addition, we employ clustering and symbolic representation procedures that compress the unsafe regions into a compact representation. This, in turn, allows to temporarily activate the shield solely in (potentially) unsafe regions, in an efficient manner. Our novel approach allows to significantly reduce runtime overhead while still preserving formal safety guarantees. We extensively evaluate our approach on two benchmarks from the robotic navigation domain, as well as provide an in-depth analysis of its scalability and completeness. 1more » « less
-
Over the past decade, deep reinforcement learning (RL) techniques have significantly advanced robotic systems. However, due to the complex architectures of neural network models, ensuring their trustworthiness is a considerable challenge. Programmatic reinforcement learning has surfaced as a promising approach. Nonetheless, synthesizing robot-control programs remains challenging. Existing methods rely on domain-specific languages (DSLs) populated with user-defined state abstraction predicates and a library of low-level controllers as abstract actions to boot synthesis, which is impractical in unknown environments that lack such predefined components. To address this limitation, we introduce RoboScribe, a novel abstraction refinement-guided program synthesis framework that automatically derives robot state and action abstractions from raw, unsegmented task demonstrations in high-dimensional, continuous spaces. It iteratively enriches and refines an initially coarse abstraction until it generates a task-solving program over the abstracted robot environment. RoboScribe is effective in synthesizing iterative programs by inferring recurring subroutines directly from the robot’s raw, continuous state and action spaces, without needing predefined abstractions. Experimental results show that RoboScribe programs inductively generalize to long-horizon robot tasks involving arbitrary numbers of objects, outperforming baseline methods in terms of both interpretability and efficiency.more » « less
-
We introduce VELM, a reinforcement learning (RL) framework grounded in verification principles for safe exploration in unknown environments. VELM ensures that an RL agent systematically explores its environment, adhering to safety properties throughout the learning process. VELM learns environment models as symbolic formulas and conducts formal reachability analysis over the learned models for safety verification. An online shielding layer is then constructed to confine the RL agent’s exploration solely within a state space verified as safe in the learned model, thereby bolstering the overall safety profile of the RL system. Our experimental results demonstrate the efficacy of VELM across diverse RL environments, highlighting its capacity to significantly reduce safety violations in comparison to existing safe learning techniques, all without compromising the RL agent’s reward performance.more » « less
-
Shielding is an effective method for ensuring safety in multi-agent domains; however, its applicability has previously been limited to environments for which an approximate discrete model and safety specification are known in advance. We present a method for learning shields in cooperative fully-observable multi-agent environments where neither a model nor safety specification are provided, using architectural constraints to realize several important properties of a shield. We show through a series of experiments that our learned shielding method is effective at significantly reducing safety violations, while largely maintaining the ability of an underlying reinforcement learning agent to optimize for reward.more » « less
