Full Gradient Deep Reinforcement Learning for Average-Reward Criterion

04/07/2023
by   Tejas Pagare, et al.
0

We extend the provably convergent Full Gradient DQN algorithm for discounted reward Markov decision processes from Avrachenkov et al. (2021) to average reward problems. We experimentally compare widely used RVI Q-Learning with recently proposed Differential Q-Learning in the neural function approximation setting with Full Gradient DQN and DQN. We also extend this to learn Whittle indices for Markovian restless multi-armed bandits. We observe a better convergence rate of the proposed Full Gradient variant across different tasks.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset