Countering Feedback Delays in Multi-Agent Learning
Authors: Zhengyuan Zhou, Panayotis Mertikopoulos, Nicholas Bambos, Peter W. Glynn, Claire Tomlin
NeurIPS 2017 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Our first contribution is that, in this class of games, the actual sequence of play induced by OMD-based learning converges to Nash equilibria provided that the feedback delays faced by the players are synchronous and bounded. Subsequently, to tackle fully decentralized, asynchronous environments with (possibly) unbounded delays between actions and feedback, we propose a variant of OMD which we call delayed mirror descent (DMD), and which relies on the repeated leveraging of past information. With this modification, the algorithm converges to Nash equilibria with no feedback synchronicity assumptions and even when the delays grow superlinearly relative to the horizon of play. |
| Researcher Affiliation | Academia | Zhengyuan Zhou Stanford University EMAIL Panayotis Mertikopoulos Univ. Grenoble Alpes, CNRS, Inria, LIG EMAIL Nicholas Bambos Stanford University EMAIL Peter Glynn Stanford University EMAIL Claire Tomlin UC Berkeley EMAIL |
| Pseudocode | Yes | Algorithm 1 Online Mirror Descent on Games under Delays and Algorithm 2 Delayed Mirror Descent on Games |
| Open Source Code | No | The paper does not provide any concrete access information (such as a specific link or an explicit statement of code release) for the source code of the described methodology. |
| Open Datasets | No | The paper is theoretical and does not conduct empirical studies; therefore, no dataset information for training is provided. |
| Dataset Splits | No | The paper is theoretical and does not conduct empirical studies; therefore, no dataset split information is provided. |
| Hardware Specification | No | The paper is theoretical and does not conduct empirical studies; therefore, no hardware specifications are mentioned. |
| Software Dependencies | No | The paper is theoretical and does not describe software implementations or their dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical and does not conduct empirical studies; therefore, no experimental setup details are provided. |