arXiv subjects

Desmond Chan

Publications and source records attributed to Desmond Chan.

3 recordsLinked to original sources

arXiv2026

Complex dynamics in the Sherrington-Kirkpatrick game

We study the outcome of adaptive learning of a large number of players engaging in sets of two-strategy two-player games. We are interested in typical games, and generate the payoff matrices at random at the beginning. The payoff matrices then remain fixed during the learning process. This provides a game theoretic foundation for the Sherrington-Kirkpatrick (SK) game, recently introduced by Garnier-Brun, Benzaquen and Bouchaud. The original model by these authors is a special case, with no bias towards any strategy. We here determine stability of learning for SK games with general random bias, and find that the nature of the stable state is affected by random fields. We also introduce a grand-canonical version of the SK game, in which players can choose to abstain. We determine the stability of learning for this game. Our analysis confirms that complex situations involving many players are frequently unlearnable, even if each player only chooses between two different actions. The rate with which players lose memory of past payoffs and the competitiveness of the game emerge as key parameters determining whether learning converges to a unique fixed point, whether there are many fixed points, or if the dynamics remains persistently volatile.

cond-mat.dis-nn↗

arXiv2024

Asymptotic Extinction in Large Coordination Games

We study the exploration-exploitation trade-off for large multiplayer coordination games where players strategise via Q-Learning, a common learning framework in multi-agent reinforcement learning. Q-Learning is known to have two shortcomings, namely non-convergence and potential equilibrium selection problems, when there are multiple fixed points, called Quantal Response Equilibria (QRE). Furthermore, whilst QRE have full support for finite games, it is not clear how Q-Learning behaves as the game becomes large. In this paper, we characterise the critical exploration rate that guarantees convergence to a unique fixed point, addressing the two shortcomings above. Using a generating-functional method, we show that this rate increases with the number of players and the alignment of their payoffs. For many-player coordination games with perfectly aligned payoffs, this exploration rate is roughly twice that of $p$-player zero-sum games. As for large games, we provide a structural result for QRE, which suggests that as the game size increases, Q-Learning converges to a QRE near the boundary of the simplex of the action space, a phenomenon we term asymptotic extinction, where a constant fraction of the actions are played with zero probability at a rate $o(1/N)$ for an $N$-action game.

cs.GT↗

arXiv2021

RtFPS: An Interactive Map that Visualizes and Predicts Wildfires in the US

Climate change has largely impacted our daily lives. As one of its consequences, we are experiencing more wildfires. In the year 2020, wildfires burned a record number of 8,888,297 acres in the US. To awaken people's attention to climate change, and to visualize the current risk of wildfires, We developed RtFPS, "Real-Time Fire Prediction System". It provides a real-time prediction visualization of wildfire risk at specific locations base on a Machine Learning model. It also provides interactive map features that show the historical wildfire events with environmental info.

cs.LG↗