Model-free Representation Learning and Exploration in Low-rank MDPs

• URL: http://arxiv.org/abs/2102.07035v1
• Date: Sun, 14 Feb 2021 00:06:54 GMT
• Title: Model-free Representation Learning and Exploration in Low-rank MDPs
• Authors: Aditya Modi, Jinglin Chen, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal
• Abstract summary: We present the first model-free representation learning algorithms for low rank MDPs. Key algorithmic contribution is a new minimax representation learning objective. Result can accommodate general function approximation to scale to complex environments.
• Score: 64.72023662543363
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The low rank MDP has emerged as an important model for studying representation learning and exploration in reinforcement learning. With a known representation, several model-free exploration strategies exist. In contrast, all algorithms for the unknown representation setting are model-based, thereby requiring the ability to model the full dynamics. In this work, we present the first model-free representation learning algorithms for low rank MDPs. The key algorithmic contribution is a new minimax representation learning objective, for which we provide variants with differing tradeoffs in their statistical and computational properties. We interleave this representation learning step with an exploration strategy to cover the state space in a reward-free manner. The resulting algorithms are provably sample efficient and can accommodate general function approximation to scale to complex environments.

Related papers

• On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning [85.75164588939185]
  We study the discriminative probabilistic modeling problem on a continuous domain for (multimodal) self-supervised representation learning. We conduct generalization error analysis to reveal the limitation of current InfoNCE-based contrastive loss for self-supervised representation learning.
  arXiv  Detail & Related papers  (2024-10-11T18:02:46Z)
• Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction [19.59151245929067]
  We study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We find this problem is best solved hierarchically by modelling items at a higher level of state abstraction to pixels. We make use of this to propose a fully model-based algorithm that learns a discriminative world model.
  arXiv  Detail & Related papers  (2024-08-21T17:59:31Z)
• Efficient Model-Free Exploration in Low-Rank MDPs [76.87340323826945]
  Low-Rank Markov Decision Processes offer a simple, yet expressive framework for RL with function approximation. Existing algorithms are either (1) computationally intractable, or (2) reliant upon restrictive statistical assumptions. We propose the first provably sample-efficient algorithm for exploration in Low-Rank MDPs.
  arXiv  Detail & Related papers  (2023-07-08T15:41:48Z)
• Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP [81.00800920928621]
  We study representation learning in partially observable Markov Decision Processes (POMDPs) We first present an algorithm for decodable POMDPs that combines maximum likelihood estimation (MLE) and optimism in the face of uncertainty (OFU) We then show how to adapt this algorithm to also work in the broader class of $gamma$-observable POMDPs.
  arXiv  Detail & Related papers  (2023-06-21T16:04:03Z)
• A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning [132.45959478064736]
  We propose a general framework that unifies model-based and model-free reinforcement learning. We propose a novel estimation function with decomposable structural properties for optimization-based exploration. Under our framework, a new sample-efficient algorithm namely OPtimization-based ExploRation with Approximation (OPERA) is proposed.
  arXiv  Detail & Related papers  (2022-09-30T17:59:16Z)
• PAC Reinforcement Learning for Predictive State Representations [60.00237613646686]
  We study online Reinforcement Learning (RL) in partially observable dynamical systems. We focus on the Predictive State Representations (PSRs) model, which is an expressive model that captures other well-known models. We develop a novel model-based algorithm for PSRs that can learn a near optimal policy in sample complexity scalingly.
  arXiv  Detail & Related papers  (2022-07-12T17:57:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.