research
∙
08/07/2023
Asynchronous Decentralized Q-Learning: Two Timescale Analysis By Persistence
Non-stationarity is a fundamental challenge in multi-agent reinforcement...
share
research
∙
03/16/2023
Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games
Stochastic games are a popular framework for studying multi-agent reinfo...
research
∙
10/13/2022
Nash Equilibria for Exchangeable Team against Team Games, their Mean Field Limit, and Role of Common Randomness
We study stochastic mean-field games among finite number of teams with l...
research
∙
09/13/2022
Independent Learning in Mean-Field Games: Satisficing Paths and Convergence to Subjective Equilibria
Independent learners are learning agents that naively employ single-agen...
research
∙
02/06/2022
An Asymptotically Optimal Two-Part Coding Scheme for Networked Control under Fixed-Rate Constraints
It is known that fixed rate adaptive quantizers can be used to stabilize...
research
∙
11/12/2021
Q-Learning for MDPs with General Spaces: Convergence and Near Optimality via Quantization under Weak Continuity
Reinforcement learning algorithms often require finiteness of state and ...
research
∙
10/09/2021
Satisficing Paths and Independent Multi-Agent Reinforcement Learning in Stochastic Games
In multi-agent reinforcement learning (MARL), independent learners are t...
research
∙
08/11/2021
Signaling Games in Higher Dimensions: Geometric Properties of Equilibrium Solutions
Signaling game problems investigate communication scenarios where encode...
research
∙
03/22/2021
Convergence of Finite Memory Q-Learning for POMDPs and Near Optimality of Learned Policies under Filter Stability
In this paper, for POMDPs, we provide the convergence of a Q learning al...
research
∙
03/19/2021
Zero-Delay Lossy Coding of Linear Vector Markov Sources: Optimality of Stationary Codes and Near Optimality of Finite Memory Codes
Optimal zero-delay coding (quantization) of ℝ^d-valued linearly generate...
research
∙
01/04/2021
Optimal Signaling with Mismatch in Priors of an Encoder and Decoder
We consider communications between an encoder and a decoder, viewed as t...
research
∙
12/15/2020
Signaling Games for Arbitrary Distributions: Number of Bins and Properties of Equilibria
We investigate the equilibrium behavior for the decentralized quadratic ...
research
∙
10/15/2020
Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes
In the theory of Partially Observed Markov Decision Processes (POMDPs), ...
research
∙
05/14/2020
Comparison of Information Structures for Zero-Sum Games and a Partial Converse to Blackwell Ordering in Standard Borel Spaces
In statistical decision theory involving a single decision-maker, one sa...
research
∙
05/12/2020
Quadratic Privacy-Signaling Games, Payoff Dominant Equilibria and the Information Bottleneck Problem
We introduce a privacy-signaling game problem in which a transmitter wit...
research
∙
01/20/2019
On the Number of Bins in Equilibria for Signaling Games
We investigate the equilibrium behavior for the decentralized quadratic ...
research
∙
01/09/2019