English
Related papers

Related papers: Geometric Entropic Exploration

200 papers

Suppose an agent is in a (possibly unknown) Markov Decision Process in the absence of a reward signal, what might we hope that an agent can efficiently learn to do? This work studies a broad class of objectives that are defined solely as…

Machine Learning · Computer Science 2019-01-29 Elad Hazan , Sham M. Kakade , Karan Singh , Abby Van Soest

Deep reinforcement learning (DRL) faces significant challenges in addressing the hard-exploration problems in tasks with sparse or deceptive rewards and large state spaces. These challenges severely limit the practical application of DRL.…

Machine Learning · Computer Science 2024-01-03 Guojian Wang , Faguo Wu , Xiao Zhang , Ning Guo , Zhiming Zheng

The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms. Existing algorithms for finite state and action discounted RL problems address this by assuming sufficient…

Machine Learning · Computer Science 2025-12-09 Caleb Ju , Guanghui Lan

We study risk-sensitive reinforcement learning in finite discounted MDPs with recursive entropic risk measures (ERM), where the risk parameter $\beta \neq 0$ controls the agent's risk attitude: $\beta>0$ for risk-averse and $\beta<0$ for…

Machine Learning · Computer Science 2026-05-20 Oliver Mortensen , Mohammad Sadegh Talebi

Reinforcement learning has shown great potential in generalizing over raw sensory data using only a single neural network for value optimization. There are several challenges in the current state-of-the-art reinforcement learning algorithms…

Machine Learning · Computer Science 2018-10-04 Per-Arne Andersen , Morten Goodwin , Ole-Christoffer Granmo

The problem of pure exploration in Markov decision processes has been cast as maximizing the entropy over the state distribution induced by the agent's policy, an objective that has been extensively studied. However, little attention has…

Machine Learning · Computer Science 2024-06-19 Riccardo Zamboni , Duilio Cirino , Marcello Restelli , Mirco Mutti

We approach the continuous-time mean-variance (MV) portfolio selection with reinforcement learning (RL). The problem is to achieve the best tradeoff between exploration and exploitation, and is formulated as an entropy-regularized, relaxed…

Portfolio Management · Quantitative Finance 2019-05-07 Haoran Wang , Xun Yu Zhou

Unsupervised Reinforcement Learning (RL) provides a promising paradigm for learning useful behaviors via reward-free per-training. Existing methods for unsupervised RL mainly conduct empowerment-driven skill discovery or entropy-based…

Machine Learning · Computer Science 2024-05-28 Chenjia Bai , Rushuai Yang , Qiaosheng Zhang , Kang Xu , Yi Chen , Ting Xiao , Xuelong Li

Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However,…

Machine Learning · Computer Science 2025-06-18 Ting Xiao , Jiakun Zheng , Rushuai Yang , Kang Xu , Qiaosheng Zhang , Peng Liu , Chenjia Bai

Model-based reinforcement learning (MBRL) is believed to have higher sample efficiency compared with model-free reinforcement learning (MFRL). However, MBRL is plagued by dynamics bottleneck dilemma. Dynamics bottleneck dilemma is the…

Machine Learning · Computer Science 2021-06-25 Xiyao Wang , Junge Zhang , Wenzhen Huang , Qiyue Yin

Safe exploration is crucial for the real-world application of reinforcement learning (RL). Previous works consider the safe exploration problem as Constrained Markov Decision Process (CMDP), where the policies are being optimized under…

Machine Learning · Computer Science 2021-07-12 Hao Sun , Ziping Xu , Meng Fang , Zhenghao Peng , Jiadong Guo , Bo Dai , Bolei Zhou

Zero-shot reinforcement learning (RL) algorithms aim to learn a family of policies from a reward-free dataset, and recover optimal policies for any reward function directly at test time. Naturally, the quality of the pretraining dataset…

Machine Learning · Computer Science 2026-03-27 Jiajun Hu , Nuria Armengol Urpi , Jin Cheng , Stelian Coros

Any given density matrix can be represented as an infinite number of ensembles of pure states. This leads to the natural question of how to uniquely select one out of the many, apparently equally suitable, possibilities. Following Jaynes'…

Quantum Physics · Physics 2025-04-23 Fabio Anza , James P. Crutchfield

In classical reinforcement learning, when exploring an environment, agents accept arbitrary short term loss for long term gain. This is infeasible for safety critical applications, such as robotics, where even a single unsafe action may…

Machine Learning · Computer Science 2017-01-30 Matteo Turchetta , Felix Berkenkamp , Andreas Krause

Optimistic value estimates provide one mechanism for directed exploration in reinforcement learning (RL). The agent acts greedily with respect to an estimate of the value plus what can be seen as a value bonus. The value bonus can be…

Machine Learning · Computer Science 2026-02-16 Abdul Wahab , Raksha Kumaraswamy , Martha White

Reinforcement learning has become essential for strengthening the reasoning abilities of large language models, yet current exploration mechanisms remain fundamentally misaligned with how these models actually learn. Entropy bonuses and…

Machine Learning · Computer Science 2025-12-18 Zhenwen Liang , Sidi Lu , Wenhao Yu , Kishan Panaganti , Yujun Zhou , Haitao Mi , Dong Yu

Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance it. However, RLVR training often suffers from policy…

Machine Learning · Computer Science 2026-04-20 Xiaoyun Zhang , Xiaojian Yuan , Di Huang , Wang You , Chen Hu , Jingqing Ruan , Ai Jian , Kejiang Chen , Xing Hu

The Expectation--Maximization (EM) algorithm is a simple meta-algorithm that has been used for many years as a methodology for statistical inference when there are missing measurements in the observed data or when the data is composed of…

Machine Learning · Statistics 2022-11-15 Hideitsu Hino , Shotaro Akaho , Noboru Murata

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard policy optimization methods, such as Group Relative Policy…

Machine Learning · Computer Science 2026-02-09 Pengyi Li , Elizaveta Goncharova , Andrey Kuznetsov , Ivan Oseledets

Exploration bonuses in reinforcement learning guide long-horizon exploration by defining custom intrinsic objectives. Several exploration objectives like count-based bonuses, pseudo-counts, and state-entropy maximization are non-stationary…

Machine Learning · Computer Science 2024-04-24 Roger Creus Castanyer , Joshua Romoff , Glen Berseth