Verified Probabilistic Policies for Deep Reinforcement Learning

2022-01-10 · Edoardo Bacci, David Parker

Deep reinforcement learning is an increasingly popular technique for synthesising policies to control an agent's interaction with its environment. There is also growing interest in formally verifying that such policies are correct and execute safely. Progress has been made in this area by building on existing work for verification of deep neural networks and of continuous-state dynamical systems. In this paper, we tackle the problem of verifying probabilistic policies for deep reinforcement learning, which are used to, for example, tackle adversarial environments, break symmetries and manage trade-offs. We propose an abstraction approach, based on interval Markov decision processes, that yields probabilistic guarantees on a policy's execution, and present techniques to build and solve these models using abstract interpretation, mixed-integer linear programming, entropy-based refinement and probabilistic model checking. We implement our approach and illustrate its effectiveness on a selection of reinforcement learning benchmarks.

📄 PDF Abstract BibTeX arXiv:2201.03698

Code (1)

phate09/safedrl 공식 구현 pytorch

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Probabilistic Model Checking of Stochastic Reinforcement Learning Policies

2024-03-27 · Dennis Gross, Helge Spieker

We introduce a method to verify stochastic reinforcement learning (RL) policies. This approach is compatible with any RL algorithm as long as the algorithm and its corresponding environment collectively adhere to the Mar…

model reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation

2026-06-17 · Ahmad Farooq, Kamran Iqbal arxiv

Multi-agent reinforcement learning (MARL) enables agents to develop coordination strategies through emergent communication, but neural policies lack the formal safety guarantees required for safety-critical robotic deplo…

Multi-agent Reinforcement Learning

Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies

2025-01-06 · Dennis Gross, Helge Spieker

Deep reinforcement learning (RL) policies can demonstrate unsafe behaviors and are challenging to interpret. To address these challenges, we combine RL policy model checking--a technique for determining whether RL polici…

Decision Making Deep Reinforcement Learning Reinforcement Learning (RL)Sequential Decision Making

Neurosymbolic Reinforcement Learning with Formally Verified Exploration

2020-09-26 · NeurIPS 2020 12 · Greg Anderson, Abhinav Verma, Isil Dillig, Swarat Chaudhuri

We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces. A key challenge for provably safe deep RL is that repeatedly verifying neura…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Safe Exploration

Policy Gradients for Probabilistic Constrained Reinforcement Learning

2022-10-02 · Weiqin Chen, Dharmashankar Subramanian, Santiago Paternain

This paper considers the problem of learning safe policies in the context of reinforcement learning (RL). In particular, we consider the notion of probabilistic safety. This is, we aim to design policies that maintain th…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)