paper-with-me

홈 › Papers

Safe Policy Learning from Observations

2018-09-27 · Elad Sarafian, Aviv Tamar, Sarit Kraus

In this paper, we consider the problem of learning a policy by observing numerous non-expert agents. Our goal is to extract a policy that, with high-confidence, acts better than the agents' average performance. Such a setting is important for real-world problems where expert data is scarce but non-expert data can easily be obtained, e.g. by crowdsourcing. Our approach is to pose this problem as safe policy improvement in reinforcement learning. First, we evaluate an average behavior policy and approximate its value function. Then, we develop a stochastic policy improvement algorithm that safely improves the average behavior. The primary advantages of our approach, termed Rerouted Behavior Improvement (RBI), over other safe learning methods are its stability in the presence of value estimation errors and the elimination of a policy search process. We demonstrate these advantages in the Taxi grid-world domain and in four games from the Atari learning environment.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Safe non-smooth black-box optimization with application to policy search

2020-06-08 · L4DC 2020 6 · Ilnura Usmanova, Andreas Krause, Maryam Kamgarpour

For safety-critical black-box optimization tasks, observations of the constraints and the objective are often noisy and available only for the feasible points. We propose an approach based on log barriers to find a local…

Verifiable Foundation Models for Robot Safety

2026-06-22 · Davide Corsi, Kyungmin Kim, Roy Fox arxiv

Deploying foundation models for robot control raises a central challenge: the expressive power that enables rich, multimodal perception also makes these models opaque and difficult to analyze formally, rendering them int…

Collision Avoidance

State-Wise Safe Reinforcement Learning With Pixel Observations

2023-11-03 · Simon Sinong Zhan, YiXuan Wang, Qingyuan Wu, Ruochen Jiao 외

In the context of safe exploration, Reinforcement Learning (RL) has long grappled with the challenges of balancing the tradeoff between maximizing rewards and minimizing safety violations, particularly in complex environ…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Exploration+1

Safe Reinforcement Learning in Tensor Reproducing Kernel Hilbert Space

2023-12-01 · Xiaoyuan Cheng, Boli Chen, Liz Varga, Yukun Hu

This paper delves into the problem of safe reinforcement learning (RL) in a partially observable environment with the aim of achieving safe-reachability objectives. In traditional partially observable Markov decision pro…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning

SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation

2022-01-27 · Rituraj Kaushik, Karol Arndt, Ville Kyrki

The framework of Simulation-to-real learning, i.e, learning policies in simulation and transferring those policies to the real world is one of the most promising approaches towards data-efficient learning in robotics. Ho…

Bayesian Optimization