Yuan Zhou

Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample\n Complexity

2020 · arXiv (Cornell University)

In this paper we consider the problem of learning an $\\epsilon$-optimal\npolicy for a discounted Markov Decision Process (MDP). Given an MDP with $S$\nstates, $A$ actions, the discount factor $\\gamma \\in (0,1)$, and an\napproximation threshold $\\epsilon …

Study on the Effect of Lightning Wave and Its Characteristic Parameters on the Level of Lightning Resistance of Transmission Lines

2024

The traditional method of calculating the lightning resistance level of transmission lines ignores the influence of lightning current waveform and characteristic parameters on the lightning resistance level, resulting in poor accuracy of the calculation results. …

Classification for Predicting Recidivism: Challenges and Scopes

2024

In the realm of criminal justice, recidivism pertains to individuals exhibiting persistent patterns of reoffending. This subset of repeat offenders poses a significant burden on the policing system due to its recurring nature. An ability …