홈 › Papers

Learning and Querying Fast Generative Models for Reinforcement Learning

2018-02-08 · Lars Buesing, Theophane Weber, Sebastien Racaniere, S. M. Ali Eslami, Danilo Rezende, David P. Reichert, Fabio Viola, Frederic Besse, Karol Gregor, Demis Hassabis, Daan Wierstra

A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models. We show that carefully designed generative models that learn and operate on compact state representations, so-called state-space models, substantially reduce the computational costs for predicting outcomes of sequences of actions. Extensive experiments establish that state-space models accurately capture the dynamics of Atari games from the Arcade Learning Environment from raw pixels. The computational speed-up of state-space models while maintaining high accuracy makes their application in RL feasible: We demonstrate that agents which query these models for decision making outperform strong model-free baselines on the game MSPACMAN, demonstrating the potential of using learned environment models for planning.

📄 PDF Abstract BibTeX arXiv:1802.03006

Code (0)

등록된 구현이 없습니다.

Tasks

Atari Games Decision MakingModel-based Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)State Space Models

Selective Progress-Aware Querying for Human-in-the-Loop Reinforcement Learning

2025-09-24 · Anujith Muraleedharan, Anamika J H arxiv

Human feedback can greatly accelerate robot learning, but in real-world settings, such feedback is costly and limited. Existing human-in-the-loop reinforcement learning (HiL-RL) methods often assume abundant feedback, li…

Reinforcement Learning

Generative Active Learning for Image Synthesis Personalization

2024-03-22 · Xulu Zhang, WengYu Zhang, Xiao-Yong Wei, Jinlin Wu 외

This paper presents a pilot study that explores the application of active learning, traditionally studied in the context of discriminative models, to generative models. We specifically focus on image synthesis personaliz…

Active Learning Image Generation

L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning

2023-05-23 · Kibeom Kim, Hyundo Lee, Min Whoo Lee, Moonheon Lee 외

Tasks that involve interaction with various targets are called multi-target tasks. When applying general reinforcement learning approaches for such tasks, certain targets that are difficult to access or interact with may…

General Reinforcement Learning reinforcement-learning Visual Navigation

Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation

2022-11-20 · Zhizhou Ren, Anji Liu, Yitao Liang, Jian Peng 외

Learning new task-specific skills from a few trials is a fundamental challenge for artificial intelligence. Meta reinforcement learning (meta-RL) tackles this problem by learning transferable policies that support few-sh…

Meta Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Enhancing Knowledge Retrieval with In-Context Learning and Semantic Search through Generative AI

2024-06-13 · Mohammed-Khalil Ghali, Abdelrahman Farrag, Daehan Won, Yu Jin

Retrieving and extracting knowledge from extensive research documents and large databases presents significant challenges for researchers, students, and professionals in today's information-rich era. Existing retrieval s…

In-Context Learning Information Retrieval Retrieval Text Retrieval