English
Related papers

Related papers: Q* Approximation Schemes for Batch Reinforcement L…

200 papers

We study off-policy reinforcement learning for controlling continuous-time Markov diffusion processes with discrete-time observations and actions. We consider model-free algorithms with function approximation that learn value and advantage…

Machine Learning · Computer Science 2026-04-17 Wenlong Mou

We study the problem of temporal-difference-based policy evaluation in reinforcement learning. In particular, we analyse the use of a distributional reinforcement learning algorithm, quantile temporal-difference learning (QTD), for this…

Machine Learning · Computer Science 2023-05-31 Mark Rowland , Yunhao Tang , Clare Lyle , Rémi Munos , Marc G. Bellemare , Will Dabney

Majority of off-policy reinforcement learning algorithms use overestimation bias control techniques. Most of these techniques rooted in heuristics, primarily addressing the consequences of overestimation rather than its fundamental origins.…

Machine Learning · Computer Science 2023-09-27 Arsenii Kuznetsov

In reinforcement learning, temporal difference-based algorithms can be sample-inefficient: for instance, with sparse rewards, no learning occurs until a reward is observed. This can be remedied by learning richer objects, such as a model of…

Machine Learning · Computer Science 2021-01-19 Léonard Blier , Corentin Tallec , Yann Ollivier

This paper studies accelerations in Q-learning algorithms. We propose an accelerated target update scheme by incorporating the historical iterates of Q functions. The idea is conceptually inspired by the momentum-based accelerated methods…

Machine Learning · Computer Science 2019-05-14 Bowen Weng , Huaqing Xiong , Wei Zhang

This works handles the inverse reinforcement learning problem in high-dimensional state spaces, which relies on an efficient solution of model-based high-dimensional reinforcement learning problems. To solve the computationally expensive…

Machine Learning · Computer Science 2017-08-28 Kun Li , Joel W. Burdick

Unlike their conventional use as estimators of probability density functions in reinforcement learning (RL), this paper introduces a novel function-approximation role for Gaussian mixture models (GMMs) as direct surrogates for Q-function…

Machine Learning · Computer Science 2025-12-23 Minh Vu , Konstantinos Slavakis

Convex Q-learning is a recent approach to reinforcement learning, motivated by the possibility of a firmer theory for convergence, and the possibility of making use of greater a priori knowledge regarding policy or value function structure.…

Optimization and Control · Mathematics 2022-10-18 Fan Lu , Joel Mathias , Sean Meyn , Karanjit Kalsi

In reinforcement learning for partially observable environments, many successful algorithms have been developed within the asymmetric learning paradigm. This paradigm leverages additional state information available at training time for…

Machine Learning · Computer Science 2025-09-09 Gaspard Lambrechts , Damien Ernst , Aditya Mahajan

Reinforcement learning has been widely used in many problems, including quantum control of qubits. However, such problems can, at the same time, be solved by traditional, non-machine-learning methods, such as stochastic gradient descent and…

Quantum Physics · Physics 2021-05-06 Xiao-Ming Zhang , Zezhu Wei , Raza Asad , Xu-Chen Yang , Xin Wang

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

Robust Reinforcement Learning tries to make predictions more robust to changes in the dynamics or rewards of the system. This problem is particularly important when the dynamics and rewards of the environment are estimated from the data. In…

Machine Learning · Computer Science 2022-06-15 Pierre Clavier , Stéphanie Allassonière , Erwan Le Pennec

The fine-tuning of pre-trained large language models (LLMs) using reinforcement learning (RL) is generally formulated as direct policy optimization. This approach was naturally favored as it efficiently improves a pretrained LLM, seen as an…

Many sequential decision-making problems can be formulated as shortest-path problems, where the objective is to reach a goal state from a given starting state. Heuristic search is a standard approach for solving such problems, relying on a…

Artificial Intelligence · Computer Science 2025-11-14 Gal Hadar , Forest Agostinelli , Shahaf S. Shperberg

We extend the Q-learner in Black-Scholes (QLBS) framework by incorporating risk aversion and trading costs, and propose a novel Replication Learning of Option Pricing (RLOP) approach. Both methods are fully compatible with standard…

Pricing of Securities · Quantitative Finance 2026-01-06 Ziheng Chen , Minxuan Hu , Jiayu Yi , Wenxi Sun

We show that several major algorithms of reinforcement learning (RL) fit into the framework of categorical cybernetics, that is to say, parametrised bidirectional processes. We build on our previous work in which we show that value…

Machine Learning · Computer Science 2025-09-26 Jules Hedges , Riu Rodríguez Sakamoto

Control of non-episodic, finite-horizon dynamical systems with uncertain dynamics poses a tough and elementary case of the exploration-exploitation trade-off. Bayesian reinforcement learning, reasoning about the effect of actions and future…

Machine Learning · Statistics 2016-08-12 Edgar D. Klenske , Philipp Hennig

Recent work has demonstrated that problems-- particularly imitation learning and structured prediction-- where a learner's predictions influence the input-distribution it is tested on can be naturally addressed by an interactive approach…

Machine Learning · Computer Science 2014-06-24 Stephane Ross , J. Andrew Bagnell

Widely-used deep reinforcement learning algorithms have been shown to fail in the batch setting--learning from a fixed data set without interaction with the environment. Following this result, there have been several papers showing…

Machine Learning · Computer Science 2019-10-07 Scott Fujimoto , Edoardo Conti , Mohammad Ghavamzadeh , Joelle Pineau

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
‹ Prev 1 8 9 10 Next ›