paper-with-me

홈 › Papers

Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning

2022-11-01 · Riashat Islam, Hongyu Zang, Anirudh Goyal, Alex Lamb, Kenji Kawaguchi, Xin Li, Romain Laroche, Yoshua Bengio, Remi Tachet des Combes

Goal-conditioned reinforcement learning (RL) is a promising direction for training agents that are capable of solving multiple tasks and reach a diverse set of objectives. How to \textit{specify} and \textit{ground} these goals in such a way that we can both reliably reach goals during training as well as generalize to new goals during evaluation remains an open area of research. Defining goals in the space of noisy and high-dimensional sensory inputs poses a challenge for training goal-conditioned agents, or even for generalization to novel goals. We propose to address this by learning factorial representations of goals and processing the resulting representation via a discretization bottleneck, for coarser goal specification, through an approach we call DGRL. We show that applying a discretizing bottleneck can improve performance in goal-conditioned RL setups, by experimentally evaluating this method on tasks ranging from maze environments to complex robotic navigation and manipulation. Additionally, we prove a theorem lower-bounding the expected return on out-of-distribution goals, while still allowing for specifying goals with expressive combinatorial structure.

📄 PDF Abstract BibTeX arXiv:2211.00247

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Learning Discrete State Abstractions With Deep Variational Inference

2020-03-09 · pproximateinference AABI Symposium 2021 1 · Ondrej Biza, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong

Abstraction is crucial for effective sequential decision making in domains with large state spaces. In this work, we propose an information bottleneck method for learning approximate bisimulations, a type of state abstra…

Decision MakingMulti-Goal Reinforcement LearningReinforcement LearningSequential Decision Making+1

Abstraction for Offline Goal-Conditioned Reinforcement Learning

2026-05-21 · Clarisse Wibault, Alexander Goldie, Antonio Villares, Maike Osborne 외 arxiv

Markov Decision Processes (MDPs) often exhibit significant redundancy due to symmetries and shared structure across state-goal pairs in real-world Goal-Conditioned Reinforcement Learning (GCRL). While hierarchical polici…

Reinforcement Learning

ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning

2024-07-30 · Hosung Lee, Sejin Kim, Seungpil Lee, Sanha Hwang 외

This paper introduces ARCLE, an environment designed to facilitate reinforcement learning research on the Abstraction and Reasoning Corpus (ARC). Addressing this inductive reasoning benchmark with reinforcement learning …

ARCreinforcement-learningReinforcement Learning

PcLast: Discovering Plannable Continuous Latent States

2023-11-06 · Anurag Koul, Shivakanth Sujit, Shaoru Chen, Ben Evans 외

Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-c…

Decision Making

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning

2022-04-27 · Philippe Hansen-Estruch, Amy Zhang, Ashvin Nair, Patrick Yin 외

Building generalizable goal-conditioned agents from rich observations is a key to reinforcement learning (RL) solving real world problems. Traditionally in goal-conditioned RL, an agent is provided with the exact goal th…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)