paper-with-me

Papers

Ergodicity in reinforcement learning

2026-03-11 · Dominik Baumann, Erfaun Noorani, Arsenii Mustafin, Xinyi Sheng, Bert Verbruggen, Arne Vanhoyweghen, Vincent Ginis, Thomas B. Schön arxiv

In reinforcement learning, we typically aim to optimize the expected value of the sum of rewards an agent collects over a trajectory. However, if the process generating these rewards is non-ergodic, the expected value, i.e., the average over infinitely many trajectories with a given policy, is uninformative for the average over a single, but infinitely long trajectory. Thus, if we care about how the individual agent performs during deployment, the expected value is not a good optimization objective. In this paper, we discuss the impact of non-ergodic reward processes on reinforcement learning agents through an instructive example, relate the notion of ergodic reward processes to more widely used notions of ergodic Markov chains, and present existing solutions that optimize long-term performance of individual trajectories under non-ergodic reward dynamics.

📄 PDF Abstract BibTeX arXiv:2603.10895

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Safe Exploration in Markov Decision Processes

2012-05-22 · Teodor Mihai Moldovan, Pieter Abbeel

In environments with uncertain dynamics exploration is necessary to learn how to perform well. Existing reinforcement learning algorithms provide strong exploration guarantees, but they tend to rely on an ergodicity assu…

Safe Exploration

Reinforcement Learning with Function Approximation for Non-Markov Processes

2026-01-01 · Ali Devran Kara arxiv

We study reinforcement learning methods with linear function approximation under non-Markov state and cost processes. We first consider the policy evaluation method and show that the algorithm converges under suitable er…

Reinforcement Learning

Curiosity Killed or Incapacitated the Cat and the Asymptotically Optimal Agent

2020-06-05 · Michael K. Cohen, Elliot Catt, Marcus Hutter

Reinforcement learners are agents that learn to pick actions that lead to high reward. Ideally, the value of a reinforcement learner's policy approaches optimality--where the optimal informed policy is the one which maxi…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Exploration

Spectral Ergodicity in Deep Learning Architectures via Surrogate Random Matrices

2017-04-25 · Mehmet Süzen, Cornelius Weber, Joan J. Cerdà

In this work a novel method to quantify spectral ergodicity for random matrices is presented. The new methodology combines approaches rooted in the metrics of Thirumalai-Mountain (TM) and Kullbach-Leibler (KL) divergence…

Deep Learning

'Ergodicity Economics' is Pseudoscience

2023-06-05 · Alexis Akira Toda

In a series of papers, Ole Peters and his collaborators claim that the 'conceptual basis of mainstream economic theory' is 'flawed' and that the approach they call 'ergodicity economics' gives 'reason to hope for a futur…