paper-with-me

홈 › Papers

Rapid Task-Solving in Novel Environments

2020-06-05 · ICLR 2021 1 · Sam Ritter, Ryan Faulkner, Laurent Sartran, Adam Santoro, Matt Botvinick, David Raposo

We propose the challenge of rapid task-solving in novel environments (RTS), wherein an agent must solve a series of tasks as rapidly as possible in an unfamiliar environment. An effective RTS agent must balance between exploring the unfamiliar environment and solving its current task, all while building a model of the new environment over which it can plan when faced with later tasks. While modern deep RL agents exhibit some of these abilities in isolation, none are suitable for the full RTS challenge. To enable progress toward RTS, we introduce two challenge domains: (1) a minimal RTS challenge called the Memory&Planning Game and (2) One-Shot StreetLearn Navigation, which introduces scale and complexity from real-world data. We demonstrate that state-of-the-art deep RL agents fail at RTS in both domains, and that this failure is due to an inability to plan over gathered knowledge. We develop Episodic Planning Networks (EPNs) and show that deep-RL agents with EPNs excel at RTS, outperforming the nearest baseline by factors of 2-3 and learning to navigate held-out StreetLearn maps within a single episode. We show that EPNs learn to execute a value iteration-like planning algorithm and that they generalize to situations beyond their training experience. algorithm and that they generalize to situations beyond their training experience.

📄 PDF Abstract BibTeX arXiv:2006.03662

Code (0)

등록된 구현이 없습니다.

Tasks

Navigate

Similar Papers 제목 키워드 기반

Been There, Done That: Meta-Learning with Episodic Recall

2018-05-24 · ICML 2018 7 · Samuel Ritter, Jane. X. Wang, Zeb Kurth-Nelson, Siddhant M. Jayakumar 외

Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environ…

Meta-Learning

Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving

2025-05-07 · Qi Liu, Xinhao Zheng, Renqiu Xia, Xingzhi Qi 외

As a seemingly self-explanatory task, problem-solving has been a significant component of science and engineering. However, a general yet concrete formulation of problem-solving itself is missing. With the recent develop…

Automated Theorem Proving

Graph schemas as abstractions for transfer learning, inference, and planning

2023-02-14 · J. Swaroop Guntupalli, Rajkumar Vasudeva Raju, Shrinu Kushagra, Carter Wendelken 외

Transferring latent structure from one environment or problem to another is a mechanism by which humans and animals generalize with very little data. Inspired by cognitive and neurobiological insights, we propose graph s…

Graph LearningHippocampusTransfer Learning

NAVIX: Scaling MiniGrid Environments with JAX

2024-07-28 · Eduardo Pignatelli, Jarek Liesen, Robert Tjarko Lange, Chris Lu 외

As Deep Reinforcement Learning (Deep RL) research moves towards solving large-scale worlds, efficient environment simulations become crucial for rapid experimentation. However, most existing environments struggle to scal…

CPUDeep Reinforcement LearningDiversityMeta-Learning+4

HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments

2024-01-23 · Qinhong Zhou, Sunli Chen, Yisong Wang, Haozhe Xu 외

Recent advances in high-fidelity virtual environments serve as one of the major driving forces for building intelligent embodied agents to perceive, reason and interact with the physical world. Typically, these environme…

Common Sense ReasoningDecision MakingReinforcement Learning (RL)