paper-with-me

홈 › Papers

Planning Goals for Exploration

2023-03-23 · Edward S. Hu, Richard Chang, Oleh Rybkin, Dinesh Jayaraman

Dropped into an unknown environment, what should an agent do to quickly learn about the environment and how to accomplish diverse tasks within it? We address this question within the goal-conditioned reinforcement learning paradigm, by identifying how the agent should set its goals at training time to maximize exploration. We propose "Planning Exploratory Goals" (PEG), a method that sets goals for each training episode to directly optimize an intrinsic exploration reward. PEG first chooses goal commands such that the agent's goal-conditioned policy, at its current level of training, will end up in states with high exploration potential. It then launches an exploration policy starting at those promising states. To enable this direct optimization, PEG learns world models and adapts sampling-based planning algorithms to "plan goal commands". In challenging simulated robotics environments including a multi-legged ant robot in a maze, and a robot arm on a cluttered tabletop, PEG exploration enables more efficient and effective training of goal-conditioned policies relative to baselines and ablations. Our ant successfully navigates a long maze, and the robot arm successfully builds a stack of three blocks upon command. Website: https://penn-pal-lab.github.io/peg/

📄 PDF Abstract BibTeX arXiv:2303.13002

Code (1)

penn-pal-lab/peg 공식 구현 tf

Similar Papers 제목 키워드 기반

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…

GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal Babbling

2020-01-22 · Rohan Chitnis, Tom Silver, Joshua Tenenbaum, Leslie Pack Kaelbling 외

We address the problem of efficient exploration for transition model learning in the relational model-based reinforcement learning setting without extrinsic goals or rewards. Inspired by human curiosity, we propose goal-…

Decision MakingEfficient ExplorationModel-based Reinforcement Learningreinforcement-learning+1

Learning-Augmented Model-Based Planning for Visual Exploration

2022-11-15 · Yimeng Li, Arnab Debnath, Gregory Stein, Jana Kosecka

We consider the problem of time-limited robotic exploration in previously unseen environments where exploration is limited by a predefined amount of time. We propose a novel exploration approach using learning-augmented …

model

Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning

2025-09-26 · Yajie Qi, Wei Wei, Lin Li, Lijun Zhang 외 arxiv

Real-world decision-making tasks typically occur in complex and open environments, posing significant challenges to reinforcement learning (RL) agents' exploration efficiency and long-horizon planning capabilities. A pro…

Reinforcement Learning

Multimodal LLM Guided Exploration and Active Mapping using Fisher Information

2024-10-22 · Wen Jiang, Boshu Lei, Katrina Ashton, Kostas Daniilidis

We present an active mapping system that could plan for long-horizon exploration goals and short-term actions with a 3D Gaussian Splatting (3DGS) representation. Existing methods either did not take advantage of recent d…

3DGSMotion Planning