English
Related papers

Related papers: Continuous MDP Homomorphisms and Homomorphic Polic…

200 papers

This paper introduces MDP homomorphic networks for deep reinforcement learning. MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint state-action space of an MDP. Current approaches to deep…

Machine Learning · Computer Science 2021-01-21 Elise van der Pol , Daniel E. Worrall , Herke van Hoof , Frans A. Oliehoek , Max Welling

We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. Using…

Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning. There have been a flurry of recent…

Optimization and Control · Mathematics 2024-04-12 Jiacai Liu , Wenye Li , Ke Wei

This paper introduces Multi-Agent MDP Homomorphic Networks, a class of networks that allows distributed execution using only local information, yet is able to share experience between global symmetries in the joint state-action space of…

Machine Learning · Computer Science 2022-05-02 Elise van der Pol , Herke van Hoof , Frans A. Oliehoek , Max Welling

Markov Decision Processes (MDPs) are a formal framework for modeling and solving sequential decision-making problems. In finite-time horizons such problems are relevant for instance for optimal stopping or specific supply chain problems,…

Optimization and Control · Mathematics 2024-05-07 Sara Klein , Simon Weissmann , Leif Döring

Many control tasks exhibit similar dynamics that can be modeled as having common latent structure. Hidden-Parameter Markov Decision Processes (HiP-MDPs) explicitly model this structure to improve sample efficiency in multi-task settings.…

Machine Learning · Computer Science 2021-02-15 Amy Zhang , Shagun Sodhani , Khimya Khetarpal , Joelle Pineau

We develop a generic policy gradient method with the global optimality guarantee for robust Markov Decision Processes (MDPs). While policy gradient methods are widely used for solving dynamic decision problems due to their scalable and…

Machine Learning · Computer Science 2024-11-01 Qiuhao Wang , Shaohang Xu , Chin Pang Ho , Marek Petrik

While the difficulty of reinforcement learning problems is typically related to the complexity of their state spaces, Abstraction proposes that solutions often lie in simpler underlying latent spaces. Prior works have focused on learning…

Artificial Intelligence · Computer Science 2022-10-19 Amnon Attali , Pedro Cisneros-Velarde , Marco Morales , Nancy M. Amato

Building systems that autonomously create temporal abstractions from data is a key challenge in scaling learning and planning in reinforcement learning. One popular approach for addressing this challenge is the options framework (Sutton et…

Machine Learning · Computer Science 2020-01-01 Matthew Riemer , Miao Liu , Gerald Tesauro

Abstraction plays an important role in the generalisation of knowledge and skills and is key to sample efficient learning. In this work, we study joint temporal and state abstraction in reinforcement learning, where temporally-extended…

Machine Learning · Computer Science 2022-06-09 Dongge Han , Sebastian Tschiatschek

Reinforcement learning defines the problem facing agents that learn to make good decisions through action and observation alone. To be effective problem solvers, such agents must efficiently explore vast worlds, assign credit from delayed…

Machine Learning · Computer Science 2022-03-02 David Abel

Reinforcement learning in real-world systems often involves delayed feedback, which breaks the Markov assumption and impedes both learning and control. Canonical augmentation-based approaches cause state-space explosion, which imposes a…

Machine Learning · Computer Science 2026-05-05 Jongsoo Lee , Jangwon Kim , Soohee Han

Real-world control systems require policies that are not only high-performing but also interpretable and robust. A promising direction toward this goal is model-based control, which learns system dynamics and cost functions from historical…

Systems and Control · Electrical Eng. & Systems 2025-11-20 Yuexin Bian , Jie Feng , Yuanyuan Shi

We propose a practical integration of logical state abstraction with AIXI, a Bayesian optimality notion for reinforcement learning agents, to significantly expand the model class that AIXI agents can be approximated over to complex…

Artificial Intelligence · Computer Science 2022-10-14 Samuel Yang-Zhao , Tianyu Wang , Kee Siong Ng

In this semi-tutorial paper, we first review the information-theoretic approach to account for the computational costs incurred during the search for optimal actions in a sequential decision-making problem. The traditional (MDP) framework…

Artificial Intelligence · Computer Science 2021-02-23 Daniel T. Larsson , Daniel Braun , Panagiotis Tsiotras

Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a curriculum, and enforcing measures of safety. A recently…

Artificial Intelligence · Computer Science 2022-09-16 Kyle Hollins Wray , Stas Tiomkin , Mykel J. Kochenderfer , Pieter Abbeel

We consider the problem of learning an $\varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Given access to a generative model, we achieve rate-optimal sample…

Machine Learning · Computer Science 2024-05-13 Davide Maran , Alberto Maria Metelli , Matteo Papini , Marcello Restelli

One major limitation to the applicability of Reinforcement Learning (RL) to many practical domains is the large number of samples required to learn an optimal policy. To address this problem and improve learning efficiency, we consider a…

Machine Learning · Computer Science 2023-08-07 Roberto Cipollone , Giuseppe De Giacomo , Marco Favorito , Luca Iocchi , Fabio Patrizi

This paper addresses the problem of learning abstractions that boost robot planning performance while providing strong guarantees of reliability. Although state-of-the-art hierarchical robot planning algorithms allow robots to efficiently…

Robotics · Computer Science 2022-04-26 Naman Shah , Siddharth Srivastava

This work addresses the general problem of control synthesis for continuous-space, discrete-time stochastic systems with probabilistic guarantees via finite abstractions. While established methods exist, they often trade off accuracy for…

Systems and Control · Electrical Eng. & Systems 2025-07-04 Ibon Gracia , Morteza Lahijanian