English
Related papers

Related papers: Continuous MDP Homomorphisms and Homomorphic Polic…

200 papers

Modern policy optimization methods roughly follow the policy mirror descent (PMD) algorithmic template, for which there are by now numerous theoretical convergence results. However, most of these either target tabular environments, or can…

Machine Learning · Computer Science 2025-07-08 Uri Sherman , Tomer Koren , Yishay Mansour

This paper proposes GProp, a deep reinforcement learning algorithm for continuous policies with compatible function approximation. The algorithm is based on two innovations. Firstly, we present a temporal-difference based method for…

Machine Learning · Computer Science 2015-09-11 David Balduzzi , Muhammad Ghifary

In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is…

Machine Learning · Computer Science 2025-04-15 Anthony GX-Chen , Kenneth Marino , Rob Fergus

The Bayes-Adaptive Markov Decision Process (BAMDP) formalism pursues the Bayes-optimal solution to the exploration-exploitation trade-off in reinforcement learning. As the computation of exact solutions to Bayesian reinforcement-learning…

Machine Learning · Computer Science 2022-11-01 Dilip Arumugam , Satinder Singh

In many real-world problems, the learning agent needs to learn a problem's abstractions and solution simultaneously. However, most such abstractions need to be designed and refined by hand for different problems and domains of application.…

Machine Learning · Computer Science 2022-12-09 Mehdi Dadvar , Rashmeet Kaur Nayyar , Siddharth Srivastava

Action abstractions restrict the number of legal actions available during search in multi-unit real-time adversarial games, thus allowing algorithms to focus their search on a set of promising actions. Optimal strategies derived from…

Artificial Intelligence · Computer Science 2017-11-23 Rubens O. Moraes , Levi H. S. Lelis

We revisit the finite time analysis of policy gradient methods in the one of the simplest settings: finite state and action MDPs with a policy class consisting of all stochastic policies and with exact gradient evaluations. There has been…

Machine Learning · Computer Science 2021-12-14 Jalaj Bhandari , Daniel Russo

Policy-gradient methods have received increased attention recently as a mechanism for learning to act in partially observable environments. They have shown promise for problems admitting memoryless policies but have been less successful…

Machine Learning · Computer Science 2025-12-08 Douglas Aberdeen , Jonathan Baxter

Planning in adversarial and uncertain environments can be modeled as the problem of devising strategies in stochastic perfect information games. These games are generalizations of Markov decision processes (MDPs): there are two…

Artificial Intelligence · Computer Science 2012-07-09 Krishnendu Chatterjee , Thomas A. Henzinger , Ranjit Jhala , Rupak Majumdar

We consider a Reinforcement Learning setup where an agent interacts with an environment in observation-reward-action cycles without any (esp.\ MDP) assumptions on the environment. State aggregation and more generally feature reinforcement…

Artificial Intelligence · Computer Science 2014-07-15 Marcus Hutter

While there is an extensive body of research analyzing policy gradient methods for discounted cumulative-reward MDPs, prior work on policy gradient methods for average-reward MDPs has been limited, with most existing results restricted to…

Optimization and Control · Mathematics 2026-02-23 Jongmin Lee , Ernest K. Ryu

This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…

Machine Learning · Computer Science 2022-05-17 Yue Wang , Shaofeng Zou

The abstraction of dynamical systems is a powerful tool that enables the design of feedback controllers using a correct-by-design framework. We investigate a novel scheme to obtain data-driven abstractions of discrete-time stochastic…

Systems and Control · Electrical Eng. & Systems 2024-04-15 Rudi Coppola , Andrea Peruffo , Licio Romao , Alessandro Abate , Manuel Mazo

We propose a novel hierarchical reinforcement learning framework for control with continuous state and action spaces. In our framework, the user specifies subgoal regions which are subsets of states; then, we (i) learn options that serve as…

Machine Learning · Computer Science 2021-02-26 Kishor Jothimurugan , Osbert Bastani , Rajeev Alur

Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional,…

Machine Learning · Computer Science 2015-09-24 Marvin Zhang , Zoe McCarthy , Chelsea Finn , Sergey Levine , Pieter Abbeel

A key component of model-based reinforcement learning (RL) is a dynamics model that predicts the outcomes of actions. Errors in this predictive model can degrade the performance of model-based controllers, and complex Markov decision…

Machine Learning · Computer Science 2023-06-06 Seohong Park , Sergey Levine

We reformulate the option framework as two parallel augmented MDPs. Under this novel formulation, all policy optimization algorithms can be used off the shelf to learn intra-option policies, option termination conditions, and a master…

Machine Learning · Computer Science 2019-09-12 Shangtong Zhang , Shimon Whiteson

We present new algorithms for computing and approximating bisimulation metrics in Markov Decision Processes (MDPs). Bisimulation metrics are an elegant formalism that capture behavioral equivalence between states and provide strong…

Machine Learning · Computer Science 2019-11-22 Pablo Samuel Castro

In this paper, we propose an efficient implementation of deep policy gradient method (PGM) for optimal control problems in continuous time. The proposed method has the ability to manage the allocation of computational resources, number of…

Optimization and Control · Mathematics 2025-02-25 Arash Fahim , Md. Arafatur Rahman

Robust reinforcement learning agents using high-dimensional observations must be able to identify relevant state features amidst many exogeneous distractors. A representation that captures controllability identifies these state elements by…

Machine Learning · Computer Science 2024-06-25 Max Rudolph , Caleb Chuck , Kevin Black , Misha Lvovsky , Scott Niekum , Amy Zhang