paper-with-me

홈 › Papers

Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity

2024-10-23 · Philip Amortila, Dylan J. Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi

Real-world applications of reinforcement learning often involve environments where agents operate on complex, high-dimensional observations, but the underlying (''latent'') dynamics are comparatively simple. However, outside of restrictive settings such as small latent spaces, the fundamental statistical requirements and algorithmic principles for reinforcement learning under latent dynamics are poorly understood. This paper addresses the question of reinforcement learning under $\textit{general}$ latent dynamics from a statistical and algorithmic perspective. On the statistical side, our main negative result shows that most well-studied settings for reinforcement learning with function approximation become intractable when composed with rich observations; we complement this with a positive result, identifying latent pushforward coverability as a general condition that enables statistical tractability. Algorithmically, we develop provably efficient observable-to-latent reductions -- that is, reductions that transform an arbitrary algorithm for the latent MDP into an algorithm that can operate on rich observations -- in two settings: one where the agent has access to hindsight observations of the latent dynamics [LADZ23], and one where the agent can estimate self-predictive latent models [SAGHCB20]. Together, our results serve as a first step toward a unified statistical and algorithmic theory for reinforcement learning under latent dynamics.

📄 PDF Abstract BibTeX arXiv:2410.17904

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning

2025-10-03 · Yuda Song, Dhruv Rohatgi, Aarti Singh, J. Andrew Bagnell arxiv

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leve…

Reinforcement Learning

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics

2024-05-29 · Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy

Sample-efficiency and reliability remain major bottlenecks toward wide adoption of reinforcement learning algorithms in continuous settings with high-dimensional perceptual inputs. Toward addressing these challenges, we …

reinforcement-learningReinforcement LearningRepresentation Learning

A Theoretical Analysis of Deep Q-Learning

2019-01-01 · Jianqing Fan, Zhaoran Wang, Yuchen Xie, Zhuoran Yang

Despite the great empirical success of deep reinforcement learning, its theoretical foundation is less well understood. In this work, we make the first attempt to theoretically understand the deep Q-network (DQN) algorit…

Deep Reinforcement LearningQ-LearningReinforcement Learning

XLVIN: eXecuted Latent Value Iteration Nets

2020-10-25 · Andreea Deac, Petar Veličković, Ognjen Milinković, Pierre-Luc Bacon 외

Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and unders…

Deep Reinforcement LearningGraph Representation LearningRepresentation LearningSelf-Supervised Learning

Reinforcement Learning in Reward-Mixing MDPs

2021-10-07 · NeurIPS 2021 12 · Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor

Learning a near optimal policy in a partially observable system remains an elusive challenge in contemporary reinforcement learning. In this work, we consider episodic reinforcement learning in a reward-mixing Markov dec…

Efficient Explorationreinforcement-learningReinforcement LearningReinforcement Learning (RL)