English
Related papers

Related papers: Continuous MDP Homomorphisms and Homomorphic Polic…

200 papers

Partially Observable Markov Decision Process (POMDP) is widely used to model probabilistic behavior for complex systems. Compared with MDPs, POMDP models a system more accurate but solving a POMDP generally takes exponential time in the…

Logic in Computer Science · Computer Science 2017-03-13 Xiaobin Zhang , Bo Wu , Hai Lin

Hybrid action space, which combines discrete choices and continuous parameters, is prevalent in domains such as robot control and game AI. However, efficiently modeling and optimizing hybrid discrete-continuous action space remains a…

Artificial Intelligence · Computer Science 2026-01-12 Bingyi Liu , Jinbo He , Haiyong Shi , Enshu Wang , Weizhen Han , Jingxiang Hao , Peixi Wang , Zhuangzhuang Zhang

Model-based reinforcement learning (RL) is appealing because (i) it enables planning and thus more strategic exploration, and (ii) by decoupling dynamics from rewards, it enables fast transfer to new reward functions. However, learning an…

Machine Learning · Computer Science 2020-07-14 Evan Zheran Liu , Ramtin Keramati , Sudarshan Seshadri , Kelvin Guu , Panupong Pasupat , Emma Brunskill , Percy Liang

Enabling reinforcement learning (RL) agents to leverage a knowledge base while learning from experience promises to advance RL in knowledge intensive domains. However, it has proven difficult to leverage knowledge that is not manually…

Artificial Intelligence · Computer Science 2022-05-03 Niklas Höpner , Ilaria Tiddi , Herke van Hoof

The deployment of autonomous systems in safety-critical environments requires control policies that guarantee satisfaction of complex control specifications. These systems are commonly modeled as nonlinear discrete-time stochastic systems.…

Systems and Control · Electrical Eng. & Systems 2026-04-07 Alessandro Riccardi , Thom Badings , Luca Laurenti , Alessandro Abate , Bart De Schutter

Abstraction is a desirable capability for deep learning models, which means to induce abstract concepts from concrete instances and flexibly apply them beyond the learning context. At the same time, there is a lack of clear understanding…

Machine Learning · Computer Science 2023-02-24 Shengnan An , Zeqi Lin , Bei Chen , Qiang Fu , Nanning Zheng , Jian-Guang Lou

We present metrics for measuring the similarity of states in a finite Markov decision process (MDP). The formulation of our metrics is based on the notion of bisimulation for MDPs, with an aim towards solving discounted infinite horizon…

Artificial Intelligence · Computer Science 2012-07-19 Norman Ferns , Prakash Panangaden , Doina Precup

We study the automated abstraction-based synthesis of correct-by-construction control policies for stochastic dynamical systems with unknown dynamics. Our approach is to learn an abstraction from sampled data, which is represented in the…

Systems and Control · Electrical Eng. & Systems 2025-09-03 Mahdi Nazeri , Thom Badings , Anne-Kathrin Schmuck , Sadegh Soudjani , Alessandro Abate

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

The automated synthesis of control policies for stochastic dynamical systems presents significant challenges. A standard approach is to construct a finite-state abstraction of the continuous system, typically represented as a Markov…

Systems and Control · Electrical Eng. & Systems 2025-08-26 Mahdi Nazeri , Thom Badings , Sadegh Soudjani , Alessandro Abate

Markov Decision Processes (MDPs) have been used to formulate many decision-making problems in science and engineering. The objective is to synthesize the best decision (action selection) policies to maximize expected rewards (or minimize…

Optimization and Control · Mathematics 2015-07-07 Mahmoud El Chamie , Behcet Acikmese

Learning a Markov Decision Process (MDP) from a fixed batch of trajectories is a non-trivial task whose outcome's quality depends on both the amount and the diversity of the sampled regions of the state-action space. Yet, many MDPs are…

Machine Learning · Computer Science 2022-03-08 Giorgio Angelotti , Nicolas Drougard , Caroline P. C. Chanel

We study reinforcement learning in hybrid discrete-continuous action spaces, such as settings where the discrete component selects a regime (or index) and the continuous component optimizes within it -- a structure common in robotics,…

Machine Learning · Computer Science 2026-05-15 Matias Alvo , Daniel Russo , Yash Kanoria

We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations. Specifically, we propose a momentum-based…

Machine Learning · Computer Science 2021-12-07 Zhanhong Jiang , Xian Yeow Lee , Sin Yong Tan , Kai Liang Tan , Aditya Balu , Young M. Lee , Chinmay Hegde , Soumik Sarkar

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

We study offline Reinforcement Learning in large infinite-horizon discounted Markov Decision Processes (MDPs) when the reward and transition models are linearly realizable under a known feature map. Starting from the classic linear-program…

Machine Learning · Computer Science 2024-05-24 Gergely Neu , Nneka Okolo

Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich…

Machine Learning · Computer Science 2021-10-28 Mete Kemertas , Tristan Aumentado-Armstrong

The concept of abstraction has been independently developed both in the context of AI Planning and discounted Markov Decision Processes (MDPs). However, the way abstractions are built and used in the context of Planning and MDPs is…

Artificial Intelligence · Computer Science 2024-12-04 Giuseppe Canonaco , Alberto Pozanco , Daniel Borrajo

Due to information asymmetry, finding optimal policies for Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) is hard with the complexity growing doubly exponentially in the horizon length. The challenge increases…

Machine Learning · Computer Science 2021-10-26 Hsu Kao , Vijay Subramanian

We present a methodology for formulating simplifying abstractions in machine learning systems by identifying and harnessing the utility structure of decisions. Machine learning tasks commonly involve high-dimensional output spaces (e.g.,…

Machine Learning · Computer Science 2023-03-31 Michael Poli , Stefano Massaroli , Stefano Ermon , Bryan Wilder , Eric Horvitz