Tracking Adversarial Targets
Authors: Yasin Abbasi-Yadkori, Peter Bartlett, Varun Kanade
ICML 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We study linear control problems with quadratic losses and adversarially chosen tracking targets. We present an efficient algorithm for this problem and show that, under standard conditions on the linear system, its regret with respect to an optimal linear policy grows as O(log2 T), where T is the number of rounds of the game. We also study a problem with adversarially chosen transition dynamics; we present an exponentially-weighted average algorithm for this problem, and we give regret bounds that grow as O( T). |
| Researcher Affiliation | Academia | Yasin Abbasi-Yadkori YASIN.ABBASIYADKORI@QUT.EDU.AU Queensland University of Technology Peter Bartlett BARTLETT@EECS.BERKELEY.EDU University of California, Berkeley and QUT Varun Kanade VKANADE@EECS.BERKELEY.EDU University of California, Berkeley |
| Pseudocode | Yes | Figure 1. The MDP-E Algorithm Figure 2. FTL-MDP: The Follow the Leader Algorithm for Markov Decision Processes Figure 3. The Exponentially Weighted Algorithm for Linear Quadratic Problems |
| Open Source Code | No | The paper does not provide any explicit statement or link for open-source code availability. |
| Open Datasets | No | This paper is theoretical and does not use or reference any datasets for training. |
| Dataset Splits | No | This paper is theoretical and does not mention dataset splits for validation. |
| Hardware Specification | No | This paper is theoretical and does not specify any hardware used for experiments. |
| Software Dependencies | No | This paper is theoretical and does not specify any software dependencies with version numbers. |
| Experiment Setup | No | This paper is theoretical and does not describe any experimental setup details or hyperparameters. |