English
Related papers

Related papers: The Uncertainty Bellman Equation and Exploration

200 papers

Exploration in reinforcement learning (RL) remains an open challenge. RL algorithms rely on observing rewards to train the agent, and if informative rewards are sparse the agent learns slowly or may not learn at all. To improve exploration…

Machine Learning · Computer Science 2024-11-12 Simone Parisi , Alireza Kazemipour , Michael Bowling

In reinforcement learning, the objective is almost always defined as a \emph{cumulative} function over the rewards along the process. However, there are many optimal control and reinforcement learning problems in various application fields,…

Machine Learning · Computer Science 2024-04-15 Wei Cui , Wei Yu

In recent work it is shown that Q-learning with linear function approximation is stable, in the sense of bounded parameter estimates, under the $(\varepsilon,\kappa)$-tamed Gibbs policy; $\kappa$ is inverse temperature, and $\varepsilon>0$…

Machine Learning · Computer Science 2026-02-09 Prashant Mehta , Sean Meyn

We study payoff manipulation in repeated multi-objective Stackelberg games, where a leader may strategically influence a follower's deterministic best response, e.g., by offering a share of their own payoff. We assume that the follower's…

Computer Science and Game Theory · Computer Science 2025-08-27 Phurinut Srisawad , Juergen Branke , Long Tran-Thanh

Efficient exploration remains a challenging problem in reinforcement learning, especially for tasks where extrinsic rewards from environments are sparse or even totally disregarded. Significant advances based on intrinsic motivation show…

Machine Learning · Computer Science 2024-04-03 Chenjia Bai , Peng Liu , Kaiyu Liu , Lingxiao Wang , Yingnan Zhao , Lei Han

The expected utility hypothesis is a popular concept in economics that is useful for making decisions when the payoff is uncertain. In this paper, we investigate the implications of a fluctuation theorem in the theory of expected utility.…

Statistical Mechanics · Physics 2024-01-17 Gianluca Francica , Luca Dell'Anna

Despite significant advances in the field of deep Reinforcement Learning (RL), today's algorithms still fail to learn human-level policies consistently over a set of diverse tasks such as Atari 2600 games. We identify three key challenges…

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

Considering that the decision-making environment faced by reinforcement learning (RL) agents is full of Knightian uncertainty, this paper describes the exploratory state dynamics equation in Knightian uncertainty to study the…

Optimization and Control · Mathematics 2026-01-27 Ziyu Li , Chen Fei , Weiyin Fei

Both the optimal value function and the optimal policy can be used to model an optimal controller based on the duality established by the Bellman equation. Even with this duality, no parametric model has been able to output both policy and…

Systems and Control · Electrical Eng. & Systems 2020-06-02 Jicheng Shi , Yingzhao Lian , Colin N. Jones

We propose Deep Q-Networks (DQN) with model-based exploration, an algorithm combining both model-free and model-based approaches that explores better and learns environments with sparse rewards more efficiently. DQN is a general-purpose,…

Machine Learning · Computer Science 2019-03-25 Stephen Zhen Gou , Yuyang Liu

Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\epsilon$-greedy. This contributes to the problem of high sample complexity,…

Machine Learning · Computer Science 2019-11-21 Tom Blau , Lionel Ott , Fabio Ramos

In this paper we investigate a utility maximization problem with drift uncertainty in a multivariate continuous-time Black-Scholes type financial market which may be incomplete. We impose a constraint on the admissible strategies that…

Portfolio Management · Quantitative Finance 2021-11-04 Jörn Sass , Dorothee Westphal

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Machine Learning · Computer Science 2022-11-04 Jie Wang , Rui Gao , Hongyuan Zha

An important but understudied question in economics is how people choose when facing uncertainty in the timing of events. Here we study preferences over time lotteries, in which the payment amount is certain but the payment time is…

Theoretical Economics · Economics 2021-08-20 Yonatan Berman , Mark Kirstein

In this paper we develop a general framework to analyze stochastic dynamic problems with unbounded utility functions and correlated and unbounded shocks. We obtain new results of the existence and uniqueness of solutions to the Bellman…

Theoretical Economics · Economics 2019-07-18 Juan Pablo Rincón-Zapatero

In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on…

Machine Learning · Computer Science 2020-12-22 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

Making optimal decisions under uncertainty is a shared problem among distinct fields. While optimal control is commonly studied in the framework of dynamic programming, it is approached with differing perspectives of the Bellman optimality…

Systems and Control · Electrical Eng. & Systems 2025-03-18 Thomas Banker , Nathan P. Lawrence , Ali Mesbah

Learning complex robot behaviors through interaction requires structured exploration. Planning should target interactions with the potential to optimize long-term performance, while only reducing uncertainty where conducive to this…

Machine Learning · Computer Science 2021-12-14 Tim Seyde , Wilko Schwarting , Sertac Karaman , Daniela Rus

This paper addresses the problem of utility maximization under uncertain parameters. In contrast with the classical approach, where the parameters of the model evolve freely within a given range, we constrain them via a penalty function. We…

Optimization and Control · Mathematics 2022-03-08 Ivan Guo , Nicolas Langrené , Grégoire Loeper , Wei Ning