List your company

Reinforcement Learning on Atari 49 ALE (test)

3,389Alien ScoreOPR
100.624954.3371,808.052,661.763Mar 6, 2026

Evaluation results

MethodLinks
OPRSteps=10M, Epochs=1002026.033,3892,571.25,285.73,4102,632880,04050633,8005,701.260.883.4111.723,521.520,160150,11079,421-0.643421339,2161,6481,84533,8313.217,50512,3006,7916,8302,5002,9708,75414.210036,652.57,99821,21023.41,7201,9453,700-0.67,560127.167,1141,38028,558.35,4706,720
SILSteps=50M, Frames=200M2026.032,242.21,3621,81217,984.22,259.43,084,781.71,137.825,0752,366.231.199.64527,559.56,710130,185.810,140.521.51,205.155.832.26,289.823,304.21,874.233,156.7-2.4310.82,888.310,614.634,449.21,1004,025.114,958.220.9661.2104,975.614,306.157,071.710.52,456.52,951.731,309.2-17.310,811.7340.553,314.60461,522.47,088.39,164.2
A2C2026.031,859.2739.91,981.416,083.32,0563,032,444.21,333.710,683.33,931.731.299.7501.63,857.83,464.2129,715.818,331.4-0.5039.10339.59,358.5329.228,008.1-4.3399.21,563.38,883.932,507.55.82,843.411,174.220.8210.817,605.213,03639,874.23.21,795.22,466.157,371.7-10.35,346.7305.648,131.80391,241.64,196.7124.2
PPO2026.031,475.6757.24,970.64,5312,195.13,010,1961,118.816,053.35,046.140.994.63394,418.12,837.2104,16911,370.4-13.569423.432314.14,546.1414.729,104.9-2.15115,3187,48826,64002,6507,241.620.710014,104.27,96334,40015.41,6801,00035,000-14.44,50020035,00005,0004,0005,000
ACPERSteps=50M, Frames=200M2026.03390.2424.8818.23,533.11,780.158,012.51,203.215,0252,602.459.3100118.57,790.11,307.519,918.84,777.5-9.83,113.359.831.42,342.53,919.5627.513,299.10598.15,87511,323.220,48501,0162,88820.9100657.22,224.58,9257.7804.5729.51,107.5-173,952.5270.79,562.5021,797.71,5504,278.8
DQNSteps=50M, Frames=200M2026.03227.1163.6537.58551,007.858,012.5421.120,433.32,896.746.173.2119.92,753.81,09034,3906,310.5-16.1276.8-14.422.61102,148263.312,300-4.4365.13,3403,80020,50001,0163,88818.91003,8003,4009,562.510.5804.5729.510,000-173,952.5270.79,562.5021,797.71,5504,278.8