English
Related papers

Related papers: On Bellman equations for continuous-time policy ev…

200 papers

We study the problem of Reinforcement Learning (RL) with linear function approximation, i.e. assuming the optimal action-value function is linear in a known $d$-dimensional feature mapping. Unfortunately, however, based on only this…

Machine Learning · Computer Science 2022-11-15 Zeyu Jia , Randy Jia , Dhruv Madeka , Dean P. Foster

The $Q$-function is a central quantity in many Reinforcement Learning (RL) algorithms for which RL agents behave following a (soft)-greedy policy w.r.t. to $Q$. It is a powerful tool that allows action selection without a model of the…

Machine Learning · Computer Science 2022-06-01 Nino Vieillard , Marcin Andrychowicz , Anton Raichuk , Olivier Pietquin , Matthieu Geist

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…

Machine Learning · Computer Science 2022-12-29 Tim G. J. Rudner , Vitchyr H. Pong , Rowan McAllister , Yarin Gal , Sergey Levine

Classical reinforcement learning (RL) techniques are generally concerned with the design of decision-making policies driven by the maximisation of the expected outcome. Nevertheless, this approach does not take into consideration the…

Machine Learning · Computer Science 2023-01-02 Thibaut Théate , Damien Ernst

The classical Dynamic Programming (DP) approach to optimal control problems is based on the characterization of the value function as the unique viscosity solution of a Hamilton-Jacobi-Bellman (HJB) equation. The DP scheme for the numerical…

Numerical Analysis · Mathematics 2019-04-15 Alessandro Alla , Maurizio Falcone , Luca Saluzzi

In this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control problem in a large continuous state space. It is shown that…

Machine Learning · Computer Science 2011-01-04 Michael Fairbank , Eduardo Alonso

We consider the problem of learning a set of probability distributions from the empirical Bellman dynamics in distributional reinforcement learning (RL), a class of state-of-the-art methods that estimate the distribution, as opposed to only…

Machine Learning · Computer Science 2020-12-10 Thanh Tang Nguyen , Sunil Gupta , Svetha Venkatesh

The maximum entropy principle is a powerful tool for solving underdetermined inverse problems. This paper considers the problem of discretizing a continuous distribution, which arises in various applied fields. We obtain the approximating…

Numerical Analysis · Mathematics 2020-08-05 Ken'ichiro Tanaka , Alexis Akira Toda

We present one of the first algorithms on model based reinforcement learning and trajectory optimization with free final time horizon. Grounded on the optimal control theory and Dynamic Programming, we derive a set of backward differential…

Systems and Control · Computer Science 2015-09-04 Wei Sun , Evangelos Theodorou , Panagiotis Tsiotras

Continuous-time reinforcement learning (CTRL) provides a principled framework for sequential decision-making in environments where interactions evolve continuously over time. Despite its empirical success, the theoretical understanding of…

Machine Learning · Computer Science 2025-05-22 Runze Zhao , Yue Yu , Adams Yiyue Zhu , Chen Yang , Dongruo Zhou

We propose a novel algorithmic framework for distributional reinforcement learning, based on learning finite-dimensional mean embeddings of return distributions. We derive several new algorithms for dynamic programming and…

We extend the standard reinforcement learning framework to random time horizons. While the classical setting typically assumes finite and deterministic or infinite runtimes of trajectories, we argue that multiple real-world applications…

Machine Learning · Computer Science 2025-08-15 Enric Ribera Borrell , Lorenz Richter , Christof Schütte

In this paper we consider long-run risk sensitive average cost impulse control applied to a continuous-time Feller-Markov process. Using the probabilistic approach, we show how to get a solution to a suitable continuous-time Bellman…

Optimization and Control · Mathematics 2021-04-01 Damian Jelito , Marcin Pitera , Łukasz Stettner

Solving the Hamilton-Jacobi-Bellman equation is important in many domains including control, robotics and economics. Especially for continuous control, solving this differential equation and its extension the Hamilton-Jacobi-Isaacs…

Robotics · Computer Science 2021-10-06 Michael Lutter , Boris Belousov , Shie Mannor , Dieter Fox , Animesh Garg , Jan Peters

One of the main goals of reinforcement learning (RL) is to provide a~way for physical machines to learn optimal behavior instead of being programmed. However, effective control of the machines usually requires fine time discretization. The…

Machine Learning · Computer Science 2022-07-12 Jakub Łyskawa , Paweł Wawrzyński

Value-function approximation methods that operate in batch mode have foundational importance to reinforcement learning (RL). Finite sample guarantees for these methods often crucially rely on two types of assumptions: (1) mild distribution…

Machine Learning · Computer Science 2019-05-02 Jinglin Chen , Nan Jiang

Offline reinforcement learning (RL) promises the ability to learn effective policies solely using existing, static datasets, without any costly online interaction. To do so, offline RL methods must handle distributional shift between the…

Machine Learning · Computer Science 2023-10-31 Joey Hong , Aviral Kumar , Sergey Levine

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

Off-policy Reinforcement Learning (RL) holds the promise of better data efficiency as it allows sample reuse and potentially enables safe interaction with the environment. Current off-policy policy gradient methods either suffer from high…

Machine Learning · Computer Science 2021-06-09 Samuele Tosatto , João Carvalho , Jan Peters

Temporal difference (TD) learning is often used to update the estimate of the value function which is used by RL agents to extract useful policies. In this paper, we focus on value function estimation in continual reinforcement learning. We…

Machine Learning · Computer Science 2023-12-20 Nishanth Anand , Doina Precup