paper-with-me

Papers

When should agents explore?

2021-08-26 · NeurIPS 2021 12 · Miruna Pîslar, David Szepesvari, Georg Ostrovski, Diana Borsa, Tom Schaul

Exploration remains a central challenge for reinforcement learning (RL). Virtually all existing methods share the feature of a monolithic behaviour policy that changes only gradually (at best). In contrast, the exploratory behaviours of animals and humans exhibit a rich diversity, namely including forms of switching between modes. This paper presents an initial study of mode-switching, non-monolithic exploration for RL. We investigate different modes to switch between, at what timescales it makes sense to switch, and what signals make for good switching triggers. We also propose practical algorithmic components that make the switching mechanism adaptive and robust, which enables flexibility without an accompanying hyper-parameter-tuning burden. Finally, we report a promising and detailed analysis on Atari, using two-mode exploration and switching at sub-episodic time-scales.

📄 PDF Abstract BibTeX arXiv:2108.11811

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Aggregating incoherent agents who disagree

2017-09-12 · Richard Pettigrew

In this paper, we explore how we should aggregate the degrees of belief of of a group of agents to give a single coherent set of degrees of belief, when at least some of those agents might be probabilistically incoherent…

When Should Agents Coordinate in Differentiable Sequential Decision Problems?

2026-02-03 · Caleb Probine, Su Ann Low, David Fridovich-Keil, Ufuk Topcu arxiv

Multi-robot teams must coordinate to operate effectively. When a team operates in an uncoordinated manner, and agents choose actions that are only individually optimal, the team's outcome can suffer. However, in many dom…

DCIR: Dynamic Consistency Intrinsic Reward for Multi-Agent Reinforcement Learning

2023-12-10 · Kunyang Lin, Yufeng Wang, Peihao Chen, Runhao Zeng 외

Learning optimal behavior policy for each agent in multi-agent systems is an essential yet difficult problem. Despite fruitful progress in multi-agent reinforcement learning, the challenge of addressing the dynamics of w…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningStarcraft+1

Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback

2023-04-21 · Nikhil Mehta, Milagro Teruel, Patricio Figueroa Sanz, Xin Deng 외

Many approaches to Natural Language Processing (NLP) tasks often treat them as single-step problems, where an agent receives an instruction, executes it, and is evaluated based on the final outcome. However, human langua…

AI AgentMinecraft

The Automated but Risky Game: Modeling Agent-to-Agent Negotiations and Transactions in Consumer Markets

2025-05-29 · Shenzhe Zhu, Jiao Sun, Yi Nian, Tobin South 외

AI agents are increasingly used in consumer-facing applications to assist with tasks such as product search, negotiation, and transaction execution. In this paper, we explore a future scenario where both consumers and me…