Provably efficient multi-task reinforcement learning with model transfer

Authors: Chicheng Zhang, Zhi Wang

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs). We formulate a heterogeneous multi-player RL problem, in which a group of players concurrently face similar but not necessarily identical MDPs, with a goal of improving their collective performance through inter-player information sharing. We design and analyze an algorithm based on the idea of model transfer, and provide gap-dependent and gap-independent upper and lower bounds that characterize the intrinsic complexity of the problem.
Researcher Affiliation Academia Chicheng Zhang University of Arizona chichengz@cs.arizona.edu Zhi Wang University of California San Diego zhiwang@eng.ucsd.edu
Pseudocode Yes Algorithm 1: MULTI-TASK-EULER
Open Source Code No No explicit statement or link for open-source code for the described methodology was found.
Open Datasets No As a theoretical paper, no specific dataset is used for training or evaluation. The paper describes a problem setting in tabular episodic Markov decision processes (MDPs) rather than using a concrete dataset.
Dataset Splits No As a theoretical paper, there is no mention of train/validation/test dataset splits.
Hardware Specification No As a theoretical paper, no hardware specifications for running experiments are mentioned.
Software Dependencies No As a theoretical paper, no specific software dependencies with version numbers for experimental replication are mentioned.
Experiment Setup No As a theoretical paper, no specific experimental setup details such as hyperparameters or training configurations are provided.