One-Shot Averaging for Distributed TD($λ$) Under Markov Sampling

no code implementations • 13 Mar 2024 • Haoxing Tian, Ioannis Ch. Paschalidis, Alex Olshevsky

We consider a distributed setup for reinforcement learning, where each agent has a copy of the same Markov Decision Process but transitions are sampled from the corresponding Markov chain independently by each agent.

On the Performance of Temporal Difference Learning With Neural Networks

no code implementations • 8 Dec 2023 • Haoxing Tian, Ioannis Ch. Paschalidis, Alex Olshevsky

Neural Temporal Difference (TD) Learning is an approximate temporal difference method for policy evaluation that uses a neural network for function approximation.