ResearchBenchmarksMeta-Reinforcement Learning on InvDoublePend paramsFollow39FLOPs (k)CSP-7,399.4442,810.0393,019.5143,228.97Nov 2, 2023Evaluation ResultsMethodMethodLinksFLOPs (k)Inference Time (ms)CSPInference Hardware=Int...Inference Hardware=Intel(R) Xeon(R) Gold 5218R @ 2.10GHz CPU2023.11390.37HyperInference Hardware=Int...Inference Hardware=Intel(R) Xeon(R) Gold 5218R @ 2.10GHz CPU2023.113,59012.3PEARLInference Hardware=Int...Inference Hardware=Intel(R) Xeon(R) Gold 5218R @ 2.10GHz CPU2023.11186,00025.1