Enhancing Sample Efficiency in Reinforcement Learning with Nonparametric Methods

Originally published at: Enhancing Sample Efficiency in Reinforcement Learning with Nonparametric Methods | NVIDIA Technical Blog

Recent developments in artificial intelligence and autonomous learning have shown impressive results in tasks like board games and computer games. However, the applicability of learning techniques remains mainly limited to simulated environments. One of the major causes of this inapplicability to real-world scenarios is the general sample-inefficiency and inability to guarantee the safe operation of…

For further information read the full paper, check out the code, or simply comment here below.