A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
A scalable MARL algorithm using local rewards for cooperative multi-agent learning.
NeuroMAS treats multi-agent systems as neural networks for scalable, trainable coordination.
Developed scalable ABM for complex financial markets.
New scalable MARL framework for dynamic networked systems.
Decentralized Gaussian processes for multi-agent learning.
Bayesian network approach for efficient cooperative MARL.
Dreamer 4 learns Minecraft tasks from videos alone.
MSPM uses modular agents to manage financial portfolios efficiently.
New method provides scalable safety guarantees for RL agents.
New algorithm reduces complexity in multi-agent reinforcement learning.
Graph neural networks learn decentralized controllers from data.
Agent-based modeling is a paradigm of modeling dynamic systems of interacting agents that are individually governed by specified behavioral rules. Training a model of such agents to produce an emergent behavior by specification of the emergent (as opposed to agent) behavior is easier from a demonstration perspective. W…
The practical usage of reinforcement learning agents is often bottlenecked by the duration of training time. To accelerate training, practitioners often turn to distributed reinforcement learning architectures to parallelize and accelerate the training process. However, modern methods for scalable reinforcement learnin…
Reinforcement learning (RL) is a promising data-driven approach for adaptive traffic signal control (ATSC) in complex urban traffic networks, and deep neural networks further enhance its learning power. However, centralized RL is infeasible for large-scale ATSC due to the extremely high dimension of the joint action sp…
A CNN-DRL model improves learning in finance with scalable actions.
ISMCTS-BR learns best responses in large games, approximating worst-case performance.
We aim to jointly optimize antenna tilt angle, and vertical and horizontal half-power beamwidths of the macrocells in a heterogeneous cellular network (HetNet). The interactions between the cells, most notably due to their coupled interference render this optimization prohibitively complex. Utilizing a single agent rei…
The capability to learn and adapt to changes in the driving environment is crucial for developing autonomous driving systems that are scalable beyond geo-fenced operational design domains. Deep Reinforcement Learning (RL) provides a promising and scalable framework for developing adaptive learning based solutions. Deep…
Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism…
In this paper, we explore using deep reinforcement learning for problems with multiple agents. Most existing methods for deep multi-agent reinforcement learning consider only a small number of agents. When the number of agents increases, the dimensionality of the input and control spaces increase as well, and these met…
Unified framework for planning under uncertainty using variational inference.
Sample efficiency and scalability to a large number of agents are two important goals for multi-agent reinforcement learning systems. Recent works got us closer to those goals, addressing non-stationarity of the environment from a single agent's perspective by utilizing a deep net critic which depends on all observatio…
Policy-gradient method controls multiple non-cohesive targets.
This paper proposes a novel policy for a group of agents to, individually as well as collectively, solve a multi armed bandit (MAB) problem. The policy relies solely on the information that an agent has obtained through sampling of the options on its own and through communication with neighbors. The option selection po…
Population synthesis is concerned with the generation of synthetic yet realistic representations of populations. It is a fundamental problem in the modeling of transport where the synthetic populations of micro-agents represent a key input to most agent-based models. In this paper, a new methodological framework for ho…
Decentralized Gaussian processes for multi-agent systems.
The paper tackles performative policy learning with strategic agents, improving scalability and generalizability.
One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions. Designing such reward functions is difficult in part because the user only has an implicit understanding of the task objective. This gives rise to the agent alignment problem: how do we create age…
This paper proposes a decentralized reinforcement learning method for multi-agent resource allocation.
Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification. Finding a set of reward functions to properly guide agent behaviors is particularly challenging in multi-agent scenarios. Inverse reinforcement learning provides a framework to automatically acquire suitable reward functions…
The paper formalizes and analyzes multi-agent Q-learning with value factorization.
VALAN is a lightweight and scalable software framework for deep reinforcement learning based on the SEED RL architecture. The framework facilitates the development and evaluation of embodied agents for solving grounded language understanding tasks, such as Vision-and-Language Navigation and Vision-and-Dialog Navigation…
Interactive Fiction games are text-based simulations in which an agent interacts with the world purely through natural language. They are ideal environments for studying how to extend reinforcement learning agents to meet the challenges of natural language understanding, partial observability, and action generation in …
DSVGD improves federated learning with fewer communication rounds.
We propose a mechanism for distributed resource management and interference mitigation in wireless networks using multi-agent deep reinforcement learning (RL). We equip each transmitter in the network with a deep RL agent that receives delayed observations from its associated users, while also exchanging observations w…
CausalGame benchmarks LLM agents' causal thinking in games.
This work explores the large-scale multi-agent communication mechanism under a multi-agent reinforcement learning (MARL) setting. We summarize the general categories of topology for communication structures in MARL literature, which are often manually specified. Then we propose a novel framework termed as Learning Stru…
Flexible decentralized MARL framework for cooperative multi-agent learning.
Feature maps, that preserve the global topology of arbitrary datasets, can be formed by self-organizing competing agents. So far, it has been presumed that global interaction of agents is necessary for this process. We establish that this is not the case, and that global topology can be uncovered through strictly local…
The paper addresses private and Byzantine-proof cooperative decision-making in multi-agent systems.
Learning when to communicate and doing that effectively is essential in multi-agent tasks. Recent works show that continuous communication allows efficient training with back-propagation in multi-agent scenarios, but have been restricted to fully-cooperative tasks. In this paper, we present Individualized Controlled Co…
DIGing-SGLD improves SGLD for scalable Bayesian learning in dynamic networks.
Human players in professional team sports achieve high level coordination by dynamically choosing complementary skills and executing primitive actions to perform these skills. As a step toward creating intelligent agents with this capability for fully cooperative multi-agent settings, we propose a two-level hierarchica…
A new method for offline RL using diffusion models and self-weighted guidance.
AlphaLogics mines market logic to generate interpretable alpha factors.
Multi-simulator training has contributed to the recent success of Deep Reinforcement Learning by stabilizing learning and allowing for higher training throughputs. We propose Gossip-based Actor-Learner Architectures (GALA) where several actor-learners (such as A2C agents) are organized in a peer-to-peer communication t…
We consider a team of reinforcement learning agents that concurrently operate in a common environment, and we develop an approach to efficient coordinated exploration that is suitable for problems of practical scale. Our approach builds on seed sampling (Dimakopoulou and Van Roy, 2018) and randomized value function lea…
To achieve a high learning accuracy, generative adversarial networks (GANs) must be fed by large datasets that adequately represent the data space. However, in many scenarios, the available datasets may be limited and distributed across multiple agents, each of which is seeking to learn the distribution of the data on …