Distributed Reinforcement Learning via Gossip
arXiv:1310.7610v164 citations
Originality Synthesis-oriented
AI Analysis
This work addresses distributed reinforcement learning for networked agents, but it appears incremental as it combines existing methods without major breakthroughs.
The paper tackled the problem of implementing TD(0) reinforcement learning in a distributed network of agents using a gossip mechanism, and the result was proving convergence for both discounted and average cost problems.
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.