Related papers: Gossip-based Actor-Learner Architectures for Deep …

Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning…

Machine learning over fully distributed data poses an important problem in peer-to-peer (P2P) applications. In this model we have one data record at each network node, but without the possibility to move raw data due to privacy…

It can largely benefit the reinforcement learning (RL) process of each agent if multiple geographically distributed agents perform their separate RL tasks cooperatively. Different from multi-agent reinforcement learning (MARL) where…

Deep reinforcement learning has been applied successfully to solve various real-world problems and the number of its applications in the multi-agent settings has been increasing. Multi-agent learning distinctly poses significant challenges…

As agentic platforms scale, agents are moving beyond fixed roles and predefined toolchains, creating an urgent need for flexible and decentralized coordination. Current structured communication protocols such as direct agent-to-agent…

As agentic platforms scale, agents are evolving beyond static roles and fixed toolchains, creating a growing need for flexible, decentralized coordination. Today's structured communication protocols (e.g., direct agent-to-agent messaging)…

Although gossip and random walk-based learning algorithms are widely known for decentralized learning, there has been limited theoretical and experimental analysis to understand their relative performance for different graph topologies and…

Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm…

We propose a novel framework for efficient parallelization of deep reinforcement learning algorithms, enabling these algorithms to learn from multiple actors on a single machine. The framework is algorithm agnostic and can be applied to…

Fully distributed learning schemes such as Gossip Learning (GL) are gaining momentum due to their scalability and effectiveness even in dynamic settings. However, they often imply a high utilization of communication and computing resources,…

We consider a set of learning agents in a collaborative peer-to-peer network, where each agent learns a personalized model according to its own learning objective. The question addressed in this paper is: how can agents improve upon their…

We consider the classical TD(0) algorithm implemented on a network of agents wherein the agents also incorporate the updates received from neighboring agents using a gossip-like mechanism. The combined scheme is shown to converge for both…

In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters. A key challenge is to handle the increased amount of data and extended training time. We have developed a…

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard…

Communication overhead hinders the scalability of large-scale distributed training. Gossip SGD, where each node averages only with its neighbors, is more communication-efficient than the prevalent parallel SGD. However, its convergence rate…

Large language models have advanced rapidly, but no single model excels in every area -- each has its strengths and weaknesses. Instead of relying on one model alone, we take inspiration from gossip protocols in distributed systems, where…

Bilevel optimization have gained growing interests, with numerous applications found in meta learning, minimax games, reinforcement learning, and nested composition optimization. This paper studies the problem of distributed bilevel…

In multi-agent reinforcement learning (MARL), the integration of a communication mechanism, allowing agents to better learn to coordinate their actions and converge on their objectives by sharing information. Based on an interaction graph,…

Indirect reciprocity, which means helping those who have helped others, is difficult to sustain among decentralized, self-interested LLM agents without reliable reputation systems. We address this challenge with the Agentic Linguistic…

Federated Learning is a popular approach for distributed learning due to its security and computational benefits. With the advent of powerful devices in the network edge, Gossip Learning further decentralizes Federated Learning by removing…