Distributed Reinforcement Learning via Gossip
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 discounted and average cost problems.
Code (0)
등록된 구현이 없습니다.
Tasks
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning
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 (GAL…
Deep Reinforcement LearningGPUreinforcement-learningReinforcement Learning+1Epistemic Protocols for Distributed Gossiping
Gossip protocols aim at arriving, by means of point-to-point or group communications, at a situation in which all the agents know each other's secrets. We consider distributed gossip protocols which are expressed by mean…
Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks
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 distrib…
Bilevel OptimizationFederated LearningMeta-Learningreinforcement-learning+2Common Knowledge in a Logic of Gossips
Gossip protocols aim at arriving, by means of point-to-point or group communications, at a situation in which all the agents know each other secrets. Recently a number of authors studied distributed epistemic gossip prot…
Crossover-SGD: A gossip-based communication in distributed deep learning for alleviating large mini-batch problem and enhancing scalability
Distributed deep learning is an effective way to reduce the training time of deep learning for large datasets as well as complex models. However, the limited scalability caused by network overheads makes it difficult to …