English
Related papers

Related papers: Data-Efficient Safe Policy Improvement Using Param…

200 papers

We study automated intrusion prevention using reinforcement learning. Following a novel approach, we formulate the problem of intrusion prevention as an (optimal) multiple stopping problem. This formulation gives us insight into the…

Machine Learning · Computer Science 2024-04-23 Kim Hammar , Rolf Stadler

We propose a policy improvement algorithm for Reinforcement Learning (RL) which is called Rerouted Behavior Improvement (RBI). RBI is designed to take into account the evaluation errors of the Q-function. Such errors are common in RL when…

Machine Learning · Computer Science 2019-07-12 Elad Sarafian , Aviv Tamar , Sarit Kraus

We study an important yet under-addressed problem of quickly and safely improving policies in online reinforcement learning domains. As its solution, we propose a novel exploration strategy - diverse exploration (DE), which learns and…

Machine Learning · Computer Science 2018-02-26 Andrew Cohen , Lei Yu , Robert Wright

There is a growing need for pluralistic alignment methods that can steer language models towards individual attributes and preferences. One such method, Self-Supervised Alignment with Mutual Information (SAMI), uses conditional mutual…

Computation and Language · Computer Science 2025-06-06 Soham V. Govande

A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and robustness against exploitation errors in out-of-distribution (OOD) regions. While OOD samples may capture valid…

Artificial Intelligence · Computer Science 2026-05-11 Hongqiang Lin , Dongxu Zhang , Yiding Sun , Mingzhe Li , Ning Yang , Haijun Zhang

Approximating model predictive control (MPC) policy using expert-based supervised learning techniques requires labeled training data sets sampled from the MPC policy. This is typically obtained by sampling the feasible state-space and…

Optimization and Control · Mathematics 2022-03-16 Dinesh Krishnamoorthy

This paper considers optimal control of dynamical systems which are represented by nonlinear stochastic differential equations. It is well-known that the optimal control policy for this problem can be obtained as a function of a value…

Robotics · Computer Science 2014-05-30 Oktay Arslan , Evangelos Theodorou , Panagiotis Tsiotras

We present a data-driven optimal control framework that can be viewed as a generalization of the path integral (PI) control approach. We find iterative feedback control laws without parameterization based on probabilistic representation of…

Systems and Control · Computer Science 2016-02-02 Yunpeng Pan , Evangelos A. Theodorou , Michail Kontitsis

Policy optimization methods have shown great promise in solving complex reinforcement and imitation learning tasks. While model-free methods are broadly applicable, they often require many samples to optimize complex policies. Model-based…

Artificial Intelligence · Computer Science 2017-11-23 Daniel Levy , Stefano Ermon

Multi-objective reinforcement learning (MORL) algorithms tackle sequential decision problems where agents may have different preferences over (possibly conflicting) reward functions. Such algorithms often learn a set of policies (each…

Machine Learning · Computer Science 2023-08-16 Lucas N. Alegre , Ana L. C. Bazzan , Diederik M. Roijers , Ann Nowé , Bruno C. da Silva

In this paper, we use concepts from supervisory control theory of discrete event systems to propose a method to learn optimal control policies for a finite-state Markov Decision Process (MDP) in which (only) certain sequences of actions are…

Machine Learning · Computer Science 2022-01-04 Arun Raman , Keerthan Shagrithaya , Shalabh Bhatnagar

This paper investigates a type of instability that is linked to the greedy policy improvement in approximated reinforcement learning. We show empirically that non-deterministic policy improvement can stabilize methods like LSPI by…

Artificial Intelligence · Computer Science 2016-12-23 Wendelin Böhmer , Rong Guo , Klaus Obermayer

In adaptive systems, predictors are used to anticipate changes in the systems state or behavior that may require system adaption, e.g., changing its configuration or adjusting resource allocation. Therefore, the quality of predictors is…

Logic in Computer Science · Computer Science 2024-12-17 Christel Baier , Sascha Klüppelholz , Jakob Piribauer , Robin Ziemek

The automatic synthesis of a policy through reinforcement learning (RL) from a given set of formal requirements depends on the construction of a reward signal and consists of the iterative application of many policy-improvement steps. The…

Machine Learning · Computer Science 2022-10-21 Luigi Berducci , Radu Grosu

Incorporating safety is an essential prerequisite for broadening the practical applications of reinforcement learning in real-world scenarios. To tackle this challenge, Constrained Markov Decision Processes (CMDPs) are leveraged, which…

Machine Learning · Computer Science 2023-11-03 Jaafar Mhamed , Shangding Gu

This paper introduces a method for Model Predictive Path Integral (MPPI) control that optimizes sample generation towards an optimal trajectory through Stein Variational Gradient Descent (SVGD). MPPI relies upon predictive rollout of…

Robotics · Computer Science 2026-04-01 Jace Aldrich , Odest Chadwicke Jenkins

Policy iteration is one of the classical frameworks of reinforcement learning, which requires a known initial stabilizing control. However, finding the initial stabilizing control depends on the known system model. To relax this requirement…

Systems and Control · Electrical Eng. & Systems 2025-03-20 Dongdong Li , Jiuxiang Dong

Multi-turn interaction remains challenging for online reinforcement learning. A common solution is trajectory-level optimization, which treats each trajectory as a single training sample. However, this approach can be inefficient and yield…

Artificial Intelligence · Computer Science 2025-11-18 Yuhan Chen , Yuxuan Liu , Long Zhang , Pengzhi Gao , Jian Luan , Wei Liu

Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which…

Artificial Intelligence · Computer Science 2020-02-28 Tomas Brazdil , Krishnendu Chatterjee , Petr Novotny , Jiri Vahala

Challenging manipulation tasks can be solved effectively by combining individual robot skills, which must be parameterized for the concrete physical environment and task at hand. This is time-consuming and difficult for human programmers,…

Robotics · Computer Science 2022-07-15 Benjamin Alt , Darko Katic , Rainer Jäkel , Asil Kaan Bozcuoglu , Michael Beetz