Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling accepted to AAAI2021
Our paper entitled “Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling” has been accepted to AAAI 2021. This paper provides the first such convergence analysis for two fundamental RL algorithms of policy gradient (PG) and temporal difference (TD) learning that incorporate AMSGrad updates (a standard alternative of Adam in theoretical analysis), referred to…