ResearchBenchmarksReinforcement Learning Exploration on HWRB Atari 57 Defender v1Reinforcement Learning Exploration on HWRB Atari 57 Defender v1Follow995,950ScoreLBC946,152.5971,051.25995,9501,020,848.75May 9, 2023Evaluation resultsMethodMethodLinksScoreHWRB MetricLBCScale=1BScale=1B2023.05995,9500