English
Related papers

Related papers: Continuous MDP Homomorphisms and Homomorphic Polic…

200 papers

We study Reinforcement Learning for partially observable dynamical systems using function approximation. We propose a new \textit{Partially Observable Bilinear Actor-Critic framework}, that is general enough to include models such as…

Machine Learning · Computer Science 2022-06-27 Masatoshi Uehara , Ayush Sekhari , Jason D. Lee , Nathan Kallus , Wen Sun

The objective of this chapter is to propose some retrospective analysis of the evolution of programming abstractions, from {\em procedures}, {\em objects}, {\em actors}, {\em components}, {\em services}, up to {\em agents}, %have some…

Software Engineering · Computer Science 2024-01-19 Jean-Pierre Briot

In this paper we propose a method that learns to play Pac-Man. We define a set of high-level observation and action modules. Actions are temporally extended, and multiple action modules may be in effect concurrently. A decision of the agent…

Machine Learning · Computer Science 2007-05-23 Istvan Szita , Andras Lorincz

A common technique to verify complex logic specifications for dynamical systems is the construction of symbolic abstractions: simpler, finite-state models whose behaviour mimics the one of the systems of interest. Typically, abstractions…

Systems and Control · Electrical Eng. & Systems 2023-03-30 Rudi Coppola , Andrea Peruffo , Manuel Mazo

A key approach to state abstraction is approximating behavioral metrics (notably, bisimulation metrics) in the observation space and embedding these learned distances in the representation space. While promising for robustness to…

Machine Learning · Computer Science 2025-09-10 Ziyan Luo , Tianwei Ni , Pierre-Luc Bacon , Doina Precup , Xujie Si

Learning long-range behaviors on complex high-dimensional agents is a fundamental problem in robot learning. For such tasks, we argue that transferring learned information from a morphologically simpler agent can massively improve the…

Machine Learning · Computer Science 2020-09-01 Donald J. Hejna , Pieter Abbeel , Lerrel Pinto

Reactive (memoryless) policies are sufficient in completely observable Markov decision processes (MDPs), but some kind of memory is usually necessary for optimal control of a partially observable MDP. Policies with finite memory can be…

Artificial Intelligence · Computer Science 2013-01-30 Nicolas Meuleau , Leonid Peshkin , Kee-Eung Kim , Leslie Pack Kaelbling

Partially observable Markov decision processes (POMDPs) model specific environments in sequential decision-making under uncertainty. Critically, optimal policies for POMDPs may not be robust against perturbations in the environment.…

Artificial Intelligence · Computer Science 2025-08-21 Maris F. L. Galesloot , Roman Andriushchenko , Milan Češka , Sebastian Junges , Nils Jansen

We study reinforcement learning with function approximation for large-scale Partially Observable Markov Decision Processes (POMDPs) where the state space and observation space are large or even continuous. Particularly, we consider Hilbert…

Machine Learning · Computer Science 2022-06-27 Masatoshi Uehara , Ayush Sekhari , Jason D. Lee , Nathan Kallus , Wen Sun

We present differentiable predictive control (DPC), a method for learning constrained neural control policies for linear systems with probabilistic performance guarantees. We employ automatic differentiation to obtain direct policy…

Systems and Control · Electrical Eng. & Systems 2022-01-28 Jan Drgona , Aaron Tuor , Draguna Vrabie

Finite-state abstractions are widely studied for the automated synthesis of correct-by-construction controllers for stochastic dynamical systems. However, existing abstraction methods often lead to prohibitively large finite-state models.…

Systems and Control · Electrical Eng. & Systems 2024-04-03 Thom Badings , Licio Romao , Alessandro Abate , Nils Jansen

Given a Markov decision process (MDP), we seek to learn representations for a range of policies to facilitate behavior steering at test time. As policies of an MDP are uniquely determined by their occupancy measures, we propose modeling…

Machine Learning · Computer Science 2026-02-02 Beiming Li , Sergio Rozada , Alejandro Ribeiro

The study of neural computation aims to understand the function of a neural system as an information processing machine. Neural systems are undoubtedly complex, necessitating principled and automated tools to abstract away details to…

Dynamical Systems · Mathematics 2025-07-09 Abel Sagodi , Il Memming Park

State abstraction has been an essential tool for dramatically improving the sample efficiency of reinforcement-learning algorithms. Indeed, by exposing and accentuating various types of latent structure within the environment, different…

Machine Learning · Computer Science 2021-06-18 Dilip Arumugam , Benjamin Van Roy

The goal of this paper is to obtain online abstractions for coupled multi-agent systems in a decentralized manner. A discrete model which captures the motion capabilities of each agent is derived over a bounded time-horizon, by discretizing…

Systems and Control · Electrical Eng. & Systems 2020-11-26 Dimitris Boskos , Dimos V. Dimarogonas

General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small…

Machine Learning · Computer Science 2009-12-30 Marcus Hutter

In this paper, we investigate learning temporal abstractions in cooperative multi-agent systems, using the options framework (Sutton et al, 1999). First, we address the planning problem for the decentralized POMDP represented by the…

Artificial Intelligence · Computer Science 2020-03-23 Jhelum Chakravorty , Nadeem Ward , Julien Roy , Maxime Chevalier-Boisvert , Sumana Basu , Andrei Lupu , Doina Precup

Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised…

Machine Learning · Computer Science 2016-07-18 William Montgomery , Sergey Levine

We show that the simplest actor-critic method -- a linear softmax policy updated with TD through interaction with a linear MDP, but featuring no explicit regularization or exploration -- does not merely find an optimal policy, but moreover…

Machine Learning · Computer Science 2022-03-15 Yuzheng Hu , Ziwei Ji , Matus Telgarsky

The goal of this report is to define abstractions for multi-agent systems with feedback interconnection in their dynamics. In the proposed decentralized framework, we specify a finite or countable transition system for each agent which only…

Systems and Control · Computer Science 2016-08-24 Dimitris Boskos , Dimos V. Dimarogonas