Related papers: Recurrent Structural Policy Gradient for Partially…
This paper considers a class of constrained stochastic composite optimization problems whose objective function is given by the summation of a differentiable (possibly nonconvex) component, together with a certain non-differentiable (but…
Existing Retrieval-Augmented Generation (RAG) methods for code struggle to capture the high-level architectural patterns and cross-file dependencies inherent in complex, theory-driven codebases, such as those in algorithmic game theory…
Policy gradient (PG) methods are a class of effective reinforcement learning algorithms, particularly when dealing with continuous control problems. They rely on fresh on-policy data, making them sample-inefficient and requiring…
Recent advances at the intersection of dense large graph limits and mean field games have begun to enable the scalable analysis of a broad class of dynamical sequential games with large numbers of agents. So far, results have been largely…
This paper introduces and analyzes a new class of mean-field control (\textsc{MFC}) problems in which agents interact through a \emph{fixed but controllable} network structure. In contrast with the classical \textsc{MFC} framework -- where…
In this paper, zero-sum mean-field type games (ZSMFTG) with linear dynamics and quadratic cost are studied under infinite-horizon discounted utility function. ZSMFTG are a class of games in which two decision makers whose utilities sum to…
We study policy gradient methods for reinforcement learning in non-Markovian decision processes (NMDPs), where observations and rewards depend on the entire interaction history. To handle this dependence, the agent maintains an internal…
While Attention Residuals has shown some effectiveness in addressing the widespread issue of unbounded activation growth across deep residual layers, it inevitably incurs significant communication overhead. To circumvent this bottleneck, we…
Parse graphs have been widely used in Human Pose Estimation (HPE) to model the hierarchical structure and context relations of the human body. However, such methods often suffer from parameter redundancy. More importantly, they rely on…
Financial markets are often driven by latent factors which traders cannot observe. Here, we address an algorithmic trading problem with collections of heterogeneous agents who aim to perform optimal execution or statistical arbitrage, where…
This paper investigates a mean-field game (MFG) problem for mean-variance (MV) portfolio management, highlighting a new type of relative performance encoded by the peer-based risk aversion. Specifically, the risk aversion is formulated as a…
Recommender Systems (RSs) in real-world applications often deal with billions of user interactions daily. To capture the most recent trends effectively, it is common to update the model incrementally using only the newly arrived data.…
We study provable multi-agent reinforcement learning (RL) in the general framework of partially observable stochastic games (POSGs). To circumvent the known hardness results and the use of computationally intractable oracles, we advocate…
The traditional Triangular Maximally Filtered Graph (TMFG) construction requires pre-computation and storage of a dense correlation matrix; this limits its applicability to small and medium-sized datasets. Here we identify key memory and…
Risk-sensitive reinforcement learning (RL) has become a popular tool for controlling the risk of uncertain outcomes and ensuring reliable performance in highly stochastic sequential decision-making problems. While it has been shown that…
Enabling reinforcement learning (RL) agents to leverage a knowledge base while learning from experience promises to advance RL in knowledge intensive domains. However, it has proven difficult to leverage knowledge that is not manually…
Entropy regularization has been extensively adopted to improve the efficiency, the stability, and the convergence of algorithms in reinforcement learning. This paper analyzes both quantitatively and qualitatively the impact of entropy…
The theory of Mean-Field Games is interested in the behaviour of interacting particle systems in which the individual interaction between particles (players) decreases as the size of the population increases. In recent years, it was…
We introduce a class of scalable Bayesian hierarchical models for the analysis of massive geostatistical datasets. The underlying idea combines ideas on high-dimensional geostatistics by partitioning the spatial domain and modeling the…
Modern machine learning models are typically trained via multi-pass stochastic gradient descent (SGD) with small batch sizes, and understanding their dynamics in high dimensions is of great interest. However, an analytical framework for…