Optimism in Face of a Context:Regret Guarantees for Stochastic Contextual MDP

Authors: Orin Levy, Yishay Mansour

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We present regret minimization algorithms for stochastic contextual MDPs under minimum reachability assumption, using an access to an offline least square regression oracle. We analyze three different settings: where the dynamics is known, where the dynamics is unknown but independent of the context and the most challenging setting where the dynamics is unknown and context-dependent. For the latter, our algorithm obtains regret bound of e O((H + 1/pmin)H|S|3/2p|A|T log(max{|G|, |P|}/δ)) with probability 1 δ, where P and G are finite and realizable function classes used to approximate the dynamics and rewards respectively, pmin is the minimum reachability parameter, S is the set of states, A the set of actions, H the horizon, and T the number of episodes.
Researcher Affiliation Collaboration Orin Levy1, Yishay Mansour1,2 1 Tel Aviv University 2 Google Research, Tel Aviv
Pseudocode Yes Algorithm 1: Regret Minimization for CMDP with Known Dynamics (RM-KD)
Open Source Code No The paper is theoretical and does not mention releasing open-source code for the described algorithms.
Open Datasets No The paper is theoretical and does not mention the use of any datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not mention any training/validation/test dataset splits.
Hardware Specification No The paper is theoretical and does not mention any specific hardware specifications used for experiments.
Software Dependencies No The paper is theoretical and describes algorithms conceptually, but does not list any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not include details about an experimental setup, hyperparameters, or system-level training settings.