paper-with-me

홈 › Papers

Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

2020-04-30 · ICML 2020 1 · Daniel Guo, Bernardo Avila Pires, Bilal Piot, Jean-bastien Grill, Florent Altché, Rémi Munos, Mohammad Gheshlaghi Azar

Learning a good representation is an essential component for deep reinforcement learning (RL). Representation learning is especially important in multitask and partially observable settings where building a representation of the unknown environment is crucial to solve the tasks. Here we introduce Prediction of Bootstrap Latents (PBL), a simple and flexible self-supervised representation learning algorithm for multitask deep RL. PBL builds on multistep predictive representations of future observations, and focuses on capturing structured information about environment dynamics. Specifically, PBL trains its representation by predicting latent embeddings of future observations. These latent embeddings are themselves trained to be predictive of the aforementioned representations. These predictions form a bootstrapping effect, allowing the agent to learn more about the key aspects of the environment dynamics. In addition, by defining prediction tasks completely in latent space, PBL provides the flexibility of using multimodal observations involving pixel images, language instructions, rewards and more. We show in our experiments that PBL delivers across-the-board improved performance over state of the art deep RL agents in the DMLab-30 and Atari-57 multitask setting.

📄 PDF Abstract BibTeX arXiv:2004.14646

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Representation Learning

Similar Papers 제목 키워드 기반

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning

2026-06-04 · Johan Obando-Ceron, Lu Li, Scott Fujimoto, Pierre-Luc Bacon 외 arxiv

Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong performance, they rely on planning and complex training pipelines, mak…

Representation LearningReinforcement LearningContinuous Control

A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning

2024-06-04 · Khimya Khetarpal, Zhaohan Daniel Guo, Bernardo Avila Pires, Yunhao Tang 외

Learning a good representation is a crucial challenge for Reinforcement Learning (RL) agents. Self-predictive learning provides means to jointly learn a latent representation and dynamics model by bootstrapping from futu…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Representation Learning

From Performance to Viability: A Bootstrap Framework for Latent-Space Representation Learning in Adaptive Biological Systems

2026-05-31 · Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit arxiv

Observable performance is commonly used to characterize biological systems. In adaptive systems, however, similar performances may arise from distinct organizations, and configurations that appear comparable at a given t…

Representation Learning

Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control

2026-08-06 · Xinwei Liu, Junyuan Liang, Jianting Zhang, Wuhui Chen arxiv

Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly improved the sample efficiency of model-f…

Representation LearningReinforcement LearningContinuous Control

TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning

2025-10-01 · Marco Bagatella, Matteo Pirotta, Ahmed Touati, Alessandro Lazaric 외 arxiv

Latent prediction--where agents learn by predicting their own latents--has emerged as a powerful paradigm for training general representations in machine learning. In reinforcement learning (RL), this approach has been e…

Reinforcement Learning