English
Related papers

Related papers: Geometry of Policy Improvement

200 papers

It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Markov decision processes (POMDPs), optimal memoryless policies…

Optimization and Control · Mathematics 2016-02-16 Guido Montufar , Keyan Ghazi-Zahedi , Nihat Ay

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

We consider the problem of finding good finite-horizon policies for POMDPs under the expected reward metric. The policies considered are {em free finite-memory policies with limited memory}; a policy is a mapping from the space of…

Artificial Intelligence · Computer Science 2013-01-30 Christopher Lusena , Tong Li , Shelia Sittinger , Chris Wells , Judy Goldsmith

We consider infinite horizon dynamic programming problems, where the control at each stage consists of several distinct decisions, each one made by one of several agents. In an earlier work we introduced a policy iteration algorithm, where…

Optimization and Control · Mathematics 2020-05-05 Dimitri Bertsekas

We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs. We propose a new algorithm, Projection-Based Constrained Policy…

Machine Learning · Computer Science 2020-10-08 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show that a potential-based reward shaping scheme is able to…

Machine Learning · Computer Science 2019-07-23 Baicen Xiao , Bhaskar Ramasubramanian , Andrew Clark , Hannaneh Hajishirzi , Linda Bushnell , Radha Poovendran

We consider a model where an agent has a repeated decision to make and wishes to maximize their total payoff. Payoffs are influenced by an action taken by the agent, but also an unknown state of the world that evolves over time. Before…

Computer Science and Game Theory · Computer Science 2021-01-20 Nicole Immorlica , Ian Kash , Brendan Lucier

We are witnessing an increasing use of data-driven predictive models to inform decisions. As decisions have implications for individuals and society, there is increasing pressure on decision makers to be transparent about their decision…

An important question in the field of AI is the extent to which successful behaviour requires an internal representation of the world. In this work, we quantify the amount of information an optimal policy provides about the underlying…

Artificial Intelligence · Computer Science 2026-02-16 Alfred Harwood , Jose Faustino , Alex Altair

We consider the task of estimating a structural model of dynamic decisions by a human agent based upon the observable history of implemented actions and visited states. This problem has an inherent nested structure: in the inner problem, an…

Machine Learning · Computer Science 2024-03-04 Siliang Zeng , Mingyi Hong , Alfredo Garcia

We study Bayesian automated mechanism design in unstructured dynamic environments, where a principal repeatedly interacts with an agent, and takes actions based on the strategic agent's report of the current state of the world. Both the…

Computer Science and Game Theory · Computer Science 2021-05-14 Hanrui Zhang , Vincent Conitzer

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…

Theoretical Economics · Economics 2020-03-24 Arthur Charpentier , Romuald Elie , Carl Remlinger

We propose an algorithm for deterministic continuous Markov Decision Processes with sparse rewards that computes the optimal policy exactly with no dependency on the size of the state space. The algorithm has time complexity of $O( |R|^3…

Machine Learning · Computer Science 2018-05-21 Joshua R. Bertram , Peng Wei

Policy Gradient (PG) algorithms are among the best candidates for the much-anticipated applications of reinforcement learning to real-world control tasks, such as robotics. However, the trial-and-error nature of these methods poses safety…

Machine Learning · Computer Science 2022-06-20 Matteo Papini , Matteo Pirotta , Marcello Restelli

Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of…

Machine Learning · Statistics 2018-06-04 Jack Umenberger , Thomas B. Schön

We report on work towards flexible algorithms for solving decision problems represented as influence diagrams. An algorithm is given to construct a tree structure for each decision node in an influence diagram. Each tree represents a…

Artificial Intelligence · Computer Science 2013-02-18 Michael C. Horsch , David L. Poole

We present an algorithm for local, regularized, policy improvement in reinforcement learning (RL) that allows us to formulate model-based and model-free variants in a single framework. Our algorithm can be interpreted as a natural extension…

We study the effect of stochasticity in on-policy policy optimization, and make the following four contributions. First, we show that the preferability of optimization methods depends critically on whether stochastic versus exact gradients…

Machine Learning · Computer Science 2021-11-01 Jincheng Mei , Bo Dai , Chenjun Xiao , Csaba Szepesvari , Dale Schuurmans

Markov decision processes (MDPs) are widely used in modeling decision making problems in stochastic environments. However, precise specification of the reward functions in MDPs is often very difficult. Recent approaches have focused on…

Artificial Intelligence · Computer Science 2012-02-20 Eunsoo Oh , Kee-Eung Kim

We study the problem of designing an optimal sequence of incentives that a principal should offer to an agent so that the agent's optimal behavior under the incentives realizes the principal's objective expressed as a temporal logic…

Optimization and Control · Mathematics 2019-03-20 Yagiz Savas , Vijay Gupta , Melkior Ornik , Lillian J. Ratliff , Ufuk Topcu
‹ Prev 1 2 3 10 Next ›