paper-with-me

홈 › Papers

Provably efficient RL with Rich Observations via Latent State Decoding

2019-01-25 · Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford

We study the exploration problem in episodic MDPs with rich observations generated from a small number of latent states. Under certain identifiability assumptions, we demonstrate how to estimate a mapping from the observations to latent states inductively through a sequence of regression and clustering steps -- where previously decoded latent states provide labels for later regression problems -- and use it to construct good exploration policies. We provide finite-sample guarantees on the quality of the learned state decoding function and exploration policies, and complement our theory with an empirical evaluation on a class of hard exploration problems. Our method exponentially improves over $Q$-learning with na\"ive exploration, even when $Q$-learning has cheating access to latent states.

📄 PDF Abstract BibTeX arXiv:1901.09018

Code (1)

Microsoft/StateDecoding 공식 구현 torch

Tasks

ClusteringQ-Learningregression

Similar Papers 제목 키워드 기반

Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics

2021-09-29 · ICLR 2022 4 · Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal 외

Many real-world applications of reinforcement learning (RL) require the agent to deal with high-dimensional observations such as those generated from a megapixel camera. Prior work has addressed such problems with repres…

Reinforcement Learning (RL)Representation Learning

Provable Rich Observation Reinforcement Learning with Combinatorial Latent States

2021-01-01 · ICLR 2021 1 · Dipendra Misra, Qinghua Liu, Chi Jin, John Langford

We propose a novel setting for reinforcement learning that combines two common real-world difficulties: presence of observations (such as camera images) and factored states (such as location of objects). In our setting, …

Contrastive Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning

2020-03-15 · NeurIPS 2020 12 · Fei Feng, Ruosong Wang, Wotao Yin, Simon S. Du 외

Motivated by the prevailing paradigm of using unsupervised learning for efficient exploration in reinforcement learning (RL) problems [tang2017exploration,bellemare2016unifying], we investigate when this paradigm is prov…

Efficient Explorationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Provable RL with Exogenous Distractors via Multistep Inverse Dynamics

2021-10-17 · Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal 외

Many real-world applications of reinforcement learning (RL) require the agent to deal with high-dimensional observations such as those generated from a megapixel camera. Prior work has addressed such problems with repres…

Reinforcement Learning (RL)Representation 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