paper-with-me

홈 › Papers

Temporally-Extended ε-Greedy Exploration

2020-06-02 · ICLR 2021 1 · Will Dabney, Georg Ostrovski, André Barreto

Recent work on exploration in reinforcement learning (RL) has led to a series of increasingly complex solutions to the problem. This increase in complexity often comes at the expense of generality. Recent empirical studies suggest that, when applied to a broader set of domains, some sophisticated exploration methods are outperformed by simpler counterparts, such as {\epsilon}-greedy. In this paper we propose an exploration algorithm that retains the simplicity of {\epsilon}-greedy while reducing dithering. We build on a simple hypothesis: the main limitation of {\epsilon}-greedy exploration is its lack of temporal persistence, which limits its ability to escape local optima. We propose a temporally extended form of {\epsilon}-greedy that simply repeats the sampled action for a random duration. It turns out that, for many duration distributions, this suffices to improve exploration on a large set of domains. Interestingly, a class of distributions inspired by ecological models of animal foraging behaviour yields particularly strong performance.

📄 PDF Abstract BibTeX arXiv:2006.01782

Code (1)

oh-lab/UTE-Uncertainty-aware-Temporal-Extension- pytorch

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Deep Exploration via Bootstrapped DQN

2016-02-15 · NeurIPS 2016 12 · Ian Osband, Charles Blundell, Alexander Pritzel, Benjamin Van Roy

Efficient exploration in complex environments remains a major challenge for reinforcement learning. We propose bootstrapped DQN, a simple algorithm that explores in a computationally and statistically efficient manner th…

Atari GamesEfficient Explorationreinforcement-learningReinforcement Learning+1

Exploitation Is All You Need... for Exploration

2025-08-02 · Micah Rentschler, Jesse Roberts arxiv

Ensuring sufficient exploration is a central challenge when training meta-reinforcement learning (meta-RL) agents to solve novel environments. Conventional solutions to the exploration-exploitation dilemma inject explici…

Reinforcement LearningMulti-Armed Bandits

Optimistic Exploration with Backward Bootstrapped Bonus for Deep Reinforcement Learning

2021-01-01 · Chenjia Bai, Lingxiao Wang, Peng Liu, Zhaoran Wang 외

Optimism in the face of uncertainty is a principled approach for provably efficient exploration for reinforcement learning in tabular and linear settings. However, such an approach is challenging in developing practical …

Atari GamesDeep Reinforcement LearningEfficient ExplorationQ-Learning+3

TIDE: A Trace-Informed Depth-First Exploration for Planning with Temporally Extended Goals

2026-01-17 · Yuliia Suprun, Khen Elimelech, Lydia E. Kavraki, Moshe Y. Vardi arxiv

Task planning with temporally extended goals (TEGs) is a critical challenge in AI and robotics, enabling agents to achieve complex sequences of objectives over time rather than addressing isolated, immediate tasks. Linea…

Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement Learning

2025-09-25 · Gawon Lee, Daesol Cho, H. Jin Kim arxiv

Multi-task reinforcement learning (MTRL) offers a promising approach to improve sample efficiency and generalization by training agents across multiple tasks, enabling knowledge sharing between them. However, applying MT…

Reinforcement Learning