Never Worse, Mostly Better: Stable Policy Improvement in Deep Reinforcement Learning. (arXiv:1910.01062v3 [cs.LG] UPDATED)

In recent years, there has been significant progress in applying deep
reinforcement learning (RL) for solving challenging problems across a wide
variety of domains. Nevertheless, convergence of various methods has been shown
to suffer from inconsistencies, due to algorithmic instability and variance, as
well as stochasticity in the benchmark environments. Particularly, despite the
fact that the agent's performance may be improving on average, it may abruptly
deteriorate at late stages of training. In this work, we study methods for
enhancing …

arxiv improvement learning lg policy reinforcement reinforcement learning