English
Related papers

Related papers: Beyond Scalar Rewards: An Axiomatic Framework for …

200 papers

Reward-free exploration is a reinforcement learning setting studied by Jin et al. (2020), who address it by running several algorithms with regret guarantees in parallel. In our work, we instead give a more natural adaptive approach for…

Machine Learning · Computer Science 2020-10-08 Emilie Kaufmann , Pierre Ménard , Omar Darwiche Domingues , Anders Jonsson , Edouard Leurent , Michal Valko

In multi-type resource allocation (MTRA) problems, there are p $\ge$ 2 types of items, and n agents, who each demand one unit of items of each type, and have strict linear preferences over bundles consisting of one item of each type. For…

Computer Science and Game Theory · Computer Science 2020-04-28 Xiaoxi Guo , Sujoy Sikdar , Haibin Wang , Lirong Xia , Yongzhi Cao , Hanpin Wang

In classic reinforcement learning (RL) and decision making problems, policies are evaluated with respect to a scalar reward function, and all optimal policies are the same with regards to their expected return. However, many real-world…

Machine Learning · Computer Science 2023-11-02 Han Shao , Lee Cohen , Avrim Blum , Yishay Mansour , Aadirupa Saha , Matthew R. Walter

We present a new geometric interpretation of Markov Decision Processes (MDPs) with a natural normalization procedure that allows us to adjust the value function at each state without altering the advantage of any action with respect to any…

Machine Learning · Computer Science 2025-03-06 Arsenii Mustafin , Aleksei Pakharev , Alex Olshevsky , Ioannis Ch. Paschalidis

In this work, we provide theoretical guarantees for reward decomposition in deterministic MDPs. Reward decomposition is a special case of Hierarchical Reinforcement Learning, that allows one to learn many policies in parallel and combine…

Machine Learning · Computer Science 2018-03-14 Tom Zahavy , Avinatan Hasidim , Haim Kaplan , Yishay Mansour

We consider the problem of finding the best memoryless stochastic policy for an infinite-horizon partially observable Markov decision process (POMDP) with finite state and action spaces with respect to either the discounted or mean reward…

Optimization and Control · Mathematics 2022-05-02 Johannes Müller , Guido Montúfar

Numerous real-world control problems involve dynamics and objectives affected by unobservable hidden parameters, ranging from autonomous driving to robotic manipulation, which cause performance degradation during sim-to-real transfer. To…

Robotics · Computer Science 2025-02-19 Morgan Byrd , Jackson Crandell , Mili Das , Jessica Inman , Robert Wright , Sehoon Ha

We study discrete-time discounted constrained Markov decision processes (CMDPs) on Borel spaces with unbounded reward functions. In our approach the transition probability functions are weakly or set-wise continuous. The reward functions…

Optimization and Control · Mathematics 2019-03-29 Eugene A. Feinberg , Anna Jaśkiewicz , Andrzej S. Nowak

Reward is the driving force for reinforcement-learning agents. This paper is dedicated to understanding the expressivity of reward as a way to capture tasks that we would want an agent to perform. We frame this study around three new…

Machine Learning · Computer Science 2022-01-19 David Abel , Will Dabney , Anna Harutyunyan , Mark K. Ho , Michael L. Littman , Doina Precup , Satinder Singh

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

Machine Learning · Computer Science 2026-03-16 Antoine Moulin , Gergely Neu , Luca Viano

In many real-world scenarios, the utility of a user is derived from the single execution of a policy. In this case, to apply multi-objective reinforcement learning, the expected utility of the returns must be optimised. Various scenarios…

Machine Learning · Computer Science 2022-07-06 Conor F. Hayes , Timothy Verstraeten , Diederik M. Roijers , Enda Howley , Patrick Mannion

We consider the problem of learning to optimize an unknown Markov decision process (MDP). We show that, if the MDP can be parameterized within some known function class, we can obtain regret bounds that scale with the dimensionality, rather…

Machine Learning · Statistics 2014-11-04 Ian Osband , Benjamin Van Roy

This paper studies Markov Decision Processes (MDPs) with atomless initial state distributions and atomless transition probabilities. Such MDPs are called atomless. The initial state distribution is considered to be fixed. We show that for…

Optimization and Control · Mathematics 2018-10-26 Eugene A. Feinberg , Aleksey B. Piunovskiy

We study online learning in episodic constrained Markov decision processes (CMDPs), where the learner aims at collecting as much reward as possible over the episodes, while satisfying some long-term constraints during the learning process.…

We consider Incentive Decision Processes, where a principal seeks to reduce its costs due to another agent's behavior, by offering incentives to the agent for alternate behavior. We focus on the case where a principal interacts with a…

Computer Science and Game Theory · Computer Science 2012-10-19 Sashank J. Reddi , Emma Brunskill

Inverse reinforcement learning is the problem of inferring a reward function from an optimal policy or demonstrations by an expert. In this work, it is assumed that the reward is expressed as a reward machine whose transitions depend on…

Machine Learning · Computer Science 2025-10-23 Mohamad Louai Shehab , Antoine Aspeel , Necmiye Ozay

Myopic exploration policies such as epsilon-greedy, softmax, or Gaussian noise fail to explore efficiently in some reinforcement learning tasks and yet, they perform well in many others. In fact, in practice, they are often selected as the…

Machine Learning · Computer Science 2022-06-22 Christoph Dann , Yishay Mansour , Mehryar Mohri , Ayush Sekhari , Karthik Sridharan

We consider a settings of hierarchical reinforcement learning, in which the reward is a sum of components. For each component we are given a policy that maximizes it and our goal is to assemble a policy from the individual policies that…

Machine Learning · Computer Science 2020-01-06 Tom Zahavy , Avinatan Hasidim , Haim Kaplan , Yishay Mansour

In robust Markov decision processes (RMDPs), it is assumed that the reward and the transition dynamics lie in a given uncertainty set. By targeting maximal return under the most adversarial model from that set, RMDPs address performance…

Machine Learning · Computer Science 2024-02-13 Uri Gadot , Esther Derman , Navdeep Kumar , Maxence Mohamed Elfatihi , Kfir Levy , Shie Mannor

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