paper-with-me

홈 › Papers

An Autonomous Non-monolithic Agent with Multi-mode Exploration based on Options Framework

2023-05-02 · Jaeyoon Kim, Junyu Xuan, Christy Liang, Farookh Hussain

Most exploration research on reinforcement learning (RL) has paid attention to the way of exploration', which is how to explore'. The other exploration research, when to explore', has not been the main focus of RL exploration research. The issue of when' of a monolithic exploration in the usual RL exploration behaviour binds an exploratory action to an exploitational action of an agent. Recently, a non-monolithic exploration research has emerged to examine the mode-switching exploration behaviour of humans and animals. The ultimate purpose of our research is to enable an agent to decide when to explore or exploit autonomously. We describe the initial research of an autonomous multi-mode exploration of non-monolithic behaviour in an options framework. The higher performance of our method is shown against the existing non-monolithic exploration method through comparative experimental results.

📄 PDF Abstract BibTeX arXiv:2305.01322

Code (1)

jangikim2/an-autonomous-non-monolithic-agent-with-multi-mode-exploration-based-on-options-framework 공식 구현 pytorch

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization

2026-05-08 · Yuping Yan, Jirui Han, Fei Ming, Yuanshuai Li 외 arxiv

Large Language Models have recently emerged as a promising paradigm for automated heuristic design for NP-hard combinatorial optimization problems. Despite this progress, existing LLM-based methods typically rely on mono…

Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features

2024-05-04 · Jaeyoon Kim, Junyu Xuan, Christy Liang, Farookh Hussain

Unsupervised pre-training has been on the lookout for the virtue of a value function representation referred to as successor features (SFs), which decouples the dynamics of the environment from the rewards. It has a sign…

Unsupervised Pre-training

ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks

2026-01-27 · Haoyun Li, Ming Xiao, Kezhi Wang, Robert Schober 외 arxiv

Emerging 6G networks rely on complex cross-layer optimization, yet manually translating high-level intents into mathematical formulations remains a bottleneck. While Large Language Models (LLMs) offer promise, monolithic…

When should agents explore?

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

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 explorato…

DiversityReinforcement Learning (RL)

ComfySearch: Autonomous Exploration and Reasoning for ComfyUI Workflows

2026-01-07 · Jinwei Su, Qizhen Lan, Zeyu Wang, Yinghui Xia 외 arxiv

AI-generated content has progressed from monolithic models to modular workflows, especially on platforms like ComfyUI, allowing users to customize complex creative pipelines. However, the large number of components in Co…