2000 character limit reached
Distributed Reinforcement Learning via Gossip (1310.7610v1)
Published 28 Oct 2013 in cs.DC, cs.AI, and math.OC
Abstract: 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.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.