ResearchBenchmarksReinforcement Learning on Atari 2600 Seaquest (Performance and Efficiency)Reinforcement Learning on Atari 2600 Seaquest (Performance and Efficiency)Follow2,300Best Stable ScoreA3C1,682.241,842.622,0032,163.38Jan 9, 2018Evaluation resultsMethodMethodLinksBest Stable ScoreTraining Time (hours)A3C2018.012,30024BA3C2018.011,84024DDRL A3C2018.011,8320.5GA3C2018.011,70624