English
Related papers

Related papers: Adapting the Exploration Rate for Value-of-Informa…

200 papers

This paper introduces a method for constructing an upper bound for exploration policy using either the weighted variance of return sequences or the weighted temporal difference (TD) error. We demonstrate that the variance of the return…

Machine Learning · Computer Science 2020-11-18 Zerong Xi , Gita Sukthankar

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

Valuation problems, such as feature interpretation, data valuation and model valuation for ensembles, become increasingly more important in many machine learning applications. Such problems are commonly solved by well-known game-theoretic…

Machine Learning · Computer Science 2022-05-13 Yatao Bian , Yu Rong , Tingyang Xu , Jiaxiang Wu , Andreas Krause , Junzhou Huang

Reinforcement Learning with Verifiable Rewards (RLVR) improves LLM reasoning, yet growing evidence indicates an exploration ceiling: it often reweights existing solution traces rather than discovering new strategies, limiting gains under…

Machine Learning · Computer Science 2026-03-03 Bizhe Bai , Xinyue Wang , Peng Ye , Tao Chen

Reinforcement learning (RL) algorithms aim to balance exploiting the current best strategy with exploring new options that could lead to higher rewards. Most common RL algorithms use undirected exploration, i.e., select random sequences of…

Machine Learning · Computer Science 2025-08-01 Bhavya Sukhija , Stelian Coros , Andreas Krause , Pieter Abbeel , Carmelo Sferrazza

Sufficient exploration is paramount for the success of a reinforcement learning agent. Yet, exploration is rarely assessed in an algorithm-independent way. We compare the behavior of three data-based, offline exploration metrics described…

Machine Learning · Computer Science 2020-10-30 Jakob J. Hollenstein , Sayantan Auddy , Matteo Saveriano , Erwan Renaudo , Justus Piater

Reward-free exploration is a reinforcement learning setting studied by Jin et al. (2020), who address it by running several algorithms with regret guarantees in parallel. In our work, we instead give a more natural adaptive approach for…

Machine Learning · Computer Science 2020-10-08 Emilie Kaufmann , Pierre Ménard , Omar Darwiche Domingues , Anders Jonsson , Edouard Leurent , Michal Valko

Efficient exploration remains a central challenge in reinforcement learning, serving as a useful pretraining objective for data collection, particularly when an external reward function is unavailable. A principled formulation of the…

Machine Learning · Computer Science 2026-03-16 Jacob Adamczyk , Adam Kamoski , Rahul V. Kulkarni

Exploration is widely regarded as one of the most challenging aspects of reinforcement learning (RL), with many naive approaches succumbing to exponential sample complexity. To isolate the challenges of exploration, we propose a new…

Machine Learning · Computer Science 2020-02-10 Chi Jin , Akshay Krishnamurthy , Max Simchowitz , Tiancheng Yu

Real-time heuristic search is a popular model of acting and learning in intelligent autonomous agents. Learning real-time search agents improve their performance over time by acquiring and refining a value function guiding the application…

Artificial Intelligence · Computer Science 2007-05-23 Vadim Bulitko

In recent years, state-of-the-art game-playing agents often involve policies that are trained in self-playing processes where Monte Carlo tree search (MCTS) algorithms and trained policies iteratively improve each other. The strongest…

Machine Learning · Computer Science 2019-05-16 Dennis J. N. J. Soemers , Éric Piette , Matthew Stephenson , Cameron Browne

The emergence of Multimodal Large Language Models (MLLMs) has propelled the development of autonomous agents that operate on Graphical User Interfaces (GUIs) using pure visual input. A fundamental challenge is robustly grounding natural…

Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration. We propose a principled way to adapt the policy for better exploration in changing…

Robotics · Computer Science 2019-05-10 Xingyu Lin , Pengsheng Guo , Carlos Florensa , David Held

To achieve sample efficiency in reinforcement learning (RL), it necessitates efficiently exploring the underlying environment. Under the offline setting, addressing the exploration challenge lies in collecting an offline dataset with…

Machine Learning · Computer Science 2022-02-15 Shuang Qiu , Jieping Ye , Zhaoran Wang , Zhuoran Yang

Proximal Policy Optimization with Adaptive Exploration (axPPO) is introduced as a novel learning algorithm. This paper investigates the exploration-exploitation tradeoff within the context of reinforcement learning and aims to contribute…

Machine Learning · Computer Science 2024-05-09 Andrei Lixandru

We study the problem of adapting to a known sub-rational opponent during online play while remaining robust to rational opponents. We focus on large imperfect-information (zero-sum) games, which makes it impossible to inspect the whole game…

Computer Science and Game Theory · Computer Science 2025-02-11 David Milec , Vojtěch Kovařík , Viliam Lisý

Exploration is a key problem in reinforcement learning. Recently bonus-based methods have achieved considerable successes in environments where exploration is difficult such as Montezuma's Revenge, which assign additional bonuses (e.g.,…

Artificial Intelligence · Computer Science 2020-09-02 Yan Song , Yingfeng Chen , Yujing Hu , Changjie Fan

Most games have, or can be generalised to have, a number of parameters that may be varied in order to provide instances of games that lead to very different player experiences. The space of possible parameter settings can be seen as a…

Artificial Intelligence · Computer Science 2017-03-21 Jialin Liu , Julian Togelius , Diego Perez-Liebana , Simon M. Lucas

We propose an adaptive incentive mechanism that learns the optimal incentives in environments where players continuously update their strategies. Our mechanism updates incentives based on each player's externality, defined as the difference…

Computer Science and Game Theory · Computer Science 2025-03-04 Chinmay Maheshwari , Kshitij Kulkarni , Manxi Wu , Shankar Sastry

We study a multi-agent decision problem in population games, where agents select from multiple available strategies and continually revise their selections based on the payoffs associated with these strategies. Unlike conventional…

Multiagent Systems · Computer Science 2024-09-17 Shinkyu Park