English
Related papers

Related papers: Policy Gradients for Probabilistic Constrained Rei…

200 papers

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues…

Machine Learning · Computer Science 2020-09-15 Daoming Lyu , Qi Qi , Mohammad Ghavamzadeh , Hengshuai Yao , Tianbao Yang , Bo Liu

Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper,…

Many sequential decision-making problems that are currently automated, such as those in manufacturing or recommender systems, operate in an environment where there is either little uncertainty, or zero risk of catastrophe. As companies and…

Machine Learning · Computer Science 2023-04-04 Marc Rigter

Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy which makes the learning performance largely affected even by minor…

Machine Learning · Computer Science 2019-07-11 Zhengyao Jiang , Shan Luo

Reinforcement learning algorithms are generally designed to maximize the expected return across a population. However, a policy that is optimal on average may be suboptimal for certain individuals, leading to potential safety concerns. To…

Machine Learning · Statistics 2026-05-26 Jingyi Li , Peng Wu , Chengchun Shi

Despite the tremendous success of Reinforcement Learning (RL) algorithms in simulation environments, applying RL to real-world applications still faces many challenges. A major concern is safety, in another word, constraint satisfaction.…

Machine Learning · Computer Science 2023-07-04 Weiye Zhao , Tairan He , Rui Chen , Tianhao Wei , Changliu Liu

We derive a policy gradient theorem for Cumulative Prospect Theory (CPT) objectives in finite-horizon Reinforcement Learning (RL), generalizing the standard policy gradient theorem and encompassing distortion-based risk objectives as…

Machine Learning · Computer Science 2026-02-18 Olivier Lepel , Anas Barakat

Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, and even hard to explicitly specify. Existing works on constraint inference rely…

Machine Learning · Computer Science 2026-05-25 Chenglin Li , Grant Ruan , Hua Geng

The alignment of autonomous agents with human values is a pivotal challenge when deploying these agents within physical environments, where safety is an important concern. However, defining the agent's objective as a reward and/or cost…

Machine Learning · Computer Science 2023-12-15 Mattijs Baert , Sam Leroux , Pieter Simoens

Safe learning and optimization deals with learning and optimization problems that avoid, as much as possible, the evaluation of non-safe input points, which are solutions, policies, or strategies that cause an irrecoverable loss (e.g.,…

Machine Learning · Computer Science 2021-06-25 Youngmin Kim , Richard Allmendinger , Manuel López-Ibáñez

Reinforcement learning (RL) agents need to be robust to variations in safety-critical environments. While system identification methods provide a way to infer the variation from online experience, they can fail in settings where fast…

Machine Learning · Computer Science 2022-03-07 Annie Xie , Shagun Sodhani , Chelsea Finn , Joelle Pineau , Amy Zhang

Since its introduction a decade ago, \emph{relative entropy policy search} (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains, not to mention providing algorithmic components used by…

Machine Learning · Computer Science 2021-03-18 Aldo Pacchiano , Jonathan Lee , Peter Bartlett , Ofir Nachum

The problem of how to take the right actions to make profits in sequential process continues to be difficult due to the quick dynamics and a significant amount of uncertainty in many application scenarios. In such complicated environments,…

Machine Learning · Computer Science 2023-10-03 Zhendong Shi , Xiaoli Wei , Ercan E. Kuruoglu

The policy gradients of the expected return objective can react slowly to rare rewards. Yet, in some cases agents may wish to emphasize the low or high returns regardless of their probability. Borrowing from the economics and control…

Machine Learning · Computer Science 2017-03-20 Chris J. Maddison , Dieterich Lawson , George Tucker , Nicolas Heess , Arnaud Doucet , Andriy Mnih , Yee Whye Teh

Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself. A natural first approach toward safe RL is to manually specify constraints on…

Machine Learning · Computer Science 2020-10-29 Krishnan Srinivasan , Benjamin Eysenbach , Sehoon Ha , Jie Tan , Chelsea Finn

We propose to leverage epistemic uncertainty about constraint satisfaction of a reinforcement learner in safety critical domains. We introduce a framework for specification of requirements for reinforcement learners in constrained settings,…

Artificial Intelligence · Computer Science 2021-02-09 Lenz Belzner , Martin Wirsing

Safe reinforcement learning (Safe RL) refers to a class of techniques that aim to prevent RL algorithms from violating constraints in the process of decision-making and exploration during trial and error. In this paper, a novel model-free…

Systems and Control · Electrical Eng. & Systems 2024-08-14 Homayoun Honari , Mehran Ghafarian Tamizi , Homayoun Najjaran

This paper focuses on finding reinforcement learning policies for control systems with hard state and action constraints. Despite its success in many domains, reinforcement learning is challenging to apply to problems with hard constraints,…

Machine Learning · Computer Science 2020-03-24 Liyuan Zheng , Yuanyuan Shi , Lillian J. Ratliff , Baosen Zhang

Given a set of trajectories demonstrating the execution of a task safely in a constrained MDP with observable rewards but with unknown constraints and non-observable costs, we aim to find a policy that maximizes the likelihood of…

Machine Learning · Computer Science 2026-03-02 George Papadopoulos , George A. Vouros

In offline reinforcement learning (RL), we learn policies from fixed datasets without environment interaction. The major challenges are to provide guarantees on the (1) performance and (2) safety of the resulting policy. A technique called…

Machine Learning · Computer Science 2026-05-12 Maris F. L. Galesloot , Thomas Rhemrev , Nils Jansen