English
Related papers

Related papers: Convergence of Q-value in case of Gaussian rewards

200 papers

In this paper we consider reinforcement learning tasks with progressive rewards; that is, tasks where the rewards tend to increase in magnitude over time. We hypothesise that this property may be problematic for value-based deep…

Machine Learning · Computer Science 2021-04-30 Michael Dann , John Thangarajah

Maximum entropy reinforcement learning integrates exploration into policy learning by providing additional intrinsic rewards proportional to the entropy of some distribution. In this paper, we propose a novel approach in which the intrinsic…

Machine Learning · Computer Science 2025-09-30 Adrien Bolland , Gaspard Lambrechts , Damien Ernst

Effective reinforcement learning requires a proper balance of exploration and exploitation defined by the dispersion of action distribution. However, this balance depends on the task, the current stage of the learning process, and the…

Machine Learning · Computer Science 2022-08-02 Paweł Wawrzyński , Wojciech Masarczyk , Mateusz Ostaszewski

We provide numerical indications of the $q$-generalised central limit theorem that has been conjectured (Tsallis 2004) in nonextensive statistical mechanics. We focus on $N$ binary random variables correlated in a {\it scale-invariant} way.…

Statistical Mechanics · Physics 2007-05-23 Luis G. Moyano , Constantino Tsallis , Murray Gell-Mann

We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner. Applications include, for example, the control of a large number of robots…

Optimization and Control · Mathematics 2025-04-30 René Carmona , Mathieu Laurière , Zongjun Tan

In this paper, we study distributional reinforcement learning from the perspective of statistical efficiency. We investigate distributional policy evaluation, aiming to estimate the complete return distribution (denoted $\eta^\pi$) attained…

Machine Learning · Statistics 2025-11-13 Liangyu Zhang , Yang Peng , Jiadong Liang , Wenhao Yang , Zhihua Zhang

In reinforcement learning, the standard criterion to evaluate policies in a state is the expectation of (discounted) sum of rewards. However, this criterion may not always be suitable, we consider an alternative criterion based on the…

Machine Learning · Computer Science 2016-11-04 Hugo Gilbert , Paul Weng

Reward-free reinforcement learning (RL) is a framework which is suitable for both the batch RL setting and the setting where there are many reward functions of interest. During the exploration phase, an agent collects samples without using…

Machine Learning · Computer Science 2020-06-22 Ruosong Wang , Simon S. Du , Lin F. Yang , Ruslan Salakhutdinov

While Bayesian-based exploration often demonstrates superior empirical performance compared to bonus-based methods in model-based reinforcement learning (RL), its theoretical understanding remains limited for model-free settings. Existing…

Machine Learning · Computer Science 2026-02-05 He Wang , Xingyu Xu , Yuejie Chi

We consider the problem of learning models for risk-sensitive reinforcement learning. We theoretically demonstrate that proper value equivalence, a method of learning models which can be used to plan optimally in the risk-neutral setting,…

Machine Learning · Computer Science 2023-12-05 Tyler Kastner , Murat A. Erdogdu , Amir-massoud Farahmand

Uncertainty quantification in reinforcement learning can greatly improve exploration and robustness. Approximate Bayesian approaches have recently been popularized to quantify uncertainty in model-free algorithms. However, so far the focus…

Machine Learning · Computer Science 2025-09-01 Pascal R. van der Vaart , Neil Yorke-Smith , Matthijs T. J. Spaan

There is accumulating evidence in the literature that stability of learning algorithms is a key characteristic that permits a learning algorithm to generalize. Despite various insightful results in this direction, there seems to be an…

Machine Learning · Statistics 2019-05-10 Karim Abou-Moustafa , Csaba Szepesvari

In real applications, the construction of prior and acceleration of sampling for posterior are usually two key points of Bayesian inversion algorithm for engineers. In this paper, q-analogy of Gaussian distribution, q-Gaussian distribution,…

Numerical Analysis · Mathematics 2018-08-06 Zhiliang Deng , Xiaomei Yang

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

Some reinforcement learning methods suffer from high sample complexity causing them to not be practical in real-world situations. $Q$-function reuse, a transfer learning method, is one way to reduce the sample complexity of learning,…

Machine Learning · Computer Science 2021-03-09 Volodymyr Tkachuk , Sriram Ganapathi Subramanian , Matthew E. Taylor

How well do reward functions learned with inverse reinforcement learning (IRL) generalize? We illustrate that state-of-the-art IRL algorithms, which maximize a maximum-entropy objective, learn rewards that overfit to the demonstrations.…

Machine Learning · Computer Science 2023-03-29 Andrew Szot , Amy Zhang , Dhruv Batra , Zsolt Kira , Franziska Meier

We propose $\textit{iterative inversion}$ -- an algorithm for learning an inverse function without input-output pairs, but only with samples from the desired output distribution and access to the forward function. The key challenge is a…

Machine Learning · Computer Science 2023-05-31 Gal Leibovich , Guy Jacob , Or Avner , Gal Novik , Aviv Tamar

We investigate the stability of equilibrium-induced optimal values with respect to (w.r.t.) reward functions $f$ and transition kernels $Q$ for time-inconsistent stopping problems under nonexponential discounting in discrete time. First,…

Optimization and Control · Mathematics 2022-05-19 Erhan Bayraktar , Zhenhua Wang , Zhou Zhou

The sum of $N$ sufficiently strongly correlated random variables will not in general be Gaussian distributed in the limit N\to\infty. We revisit examples of sums x that have recently been put forward as instances of variables obeying a…

Statistical Mechanics · Physics 2009-11-13 H. J. Hilhorst , G. Schehr

Policy gradient methods, where one searches for the policy of interest by maximizing the value functions using first-order information, become increasingly popular for sequential decision making in reinforcement learning, games, and…

Optimization and Control · Mathematics 2023-10-10 Shicong Cen , Yuejie Chi