mlsanityData to 7 Oct 2026

C-STEP: Continuous Space-Time Empowerment for Physics-informed Safe Reinforcement Learning of Mobile Agents

arXiv 2603.24241 ↗First posted 25 Mar 2026eess.SY cs.LG cs.SYcited by 0

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Safe navigation in complex environments remains a central challenge for reinforcement learning (RL) in robotics. This paper introduces Continuous Space-Time Empowerment for Physics-informed (C-STEP) safe RL, a novel measure of agent-centric safety tailored to deterministic, continuous domains. This measure can be used to design physics-informed intrinsic rewards by augmenting positive navigation reward functions. The reward incorporates the agents internal states (e.g., initial velocity) and forward dynamics to differentiate safe from risky behavior. By integrating C-STEP with navigation rewards, we obtain an intrinsic reward function that jointly optimizes task completion and collision avoidance. Numerical results demonstrate fewer collisions, reduced proximity to obstacles, and only marginal increases in travel time. Overall, C-STEP offers an interpretable, physics-informed approach to reward shaping in RL, contributing to safety for agentic mobile robotic systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 10 of its 20 references that are in the map. First posted on arXiv 25 Mar 2026.

Builds on

10 of 20 references.

References · 10

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  3. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 320
  4. 2015Variational Information Maximisation for Intrinsically Motivated Reinforcement Learningcited by 142
  5. 2013Empowerment -- an Introductioncited by 65
  6. 2021Safe Reinforcement Learning Using Robust Control Barrier Functionscited by 44
  7. 2014Changing the Environment Based on Empowerment as Intrinsic Motivationcited by 9
  8. 2023Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guaranteescited by 9
  9. 2023Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill Learningcited by 7
  10. 2021Experimental Evidence that Empowerment May Drive Exploration in Sparse-Reward Environmentscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Imagine to Ensure Safety in Hierarchical Reinforcement Learning
  2. 2023Safe Reinforcement Learning in a Simulated Robotic Arm
  3. 2024Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards
  4. 2025EigenSafe: A Spectral Framework for Learning-Based Probabilistic Safety Assessment ↗
  5. 2026Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning
  6. 2026Safe Meta-Reinforcement Learning via Information Space Reachability
  7. 2026Reward-Free Continual Adaptation for Resilient Space Robots
  8. 2021Direct Behavior Specification via Constrained Reinforcement Learning