Atari10M Comparison


bmrun________________________ user mean Breakout Seaquest Enduro SpaceInvaders Qbert Pong BeamRider commit
ppo2
       
cron 2782.3 236.9 1505.4 686.19 959.5 14234.75 20.39 1832.95 ea68f3b
acer
       
cron 3550.11 439.33 1733.13 0.0 1382.53 16234.75 20.03 5040.98 ea68f3b
a2c
       
cron 1386.22 289.9 1737.2 0.0 727.32 4461.29 18.65 2469.15 ea68f3b
trpo_mpi
       
cron 786.79 18.0 834.47 37.3 548.83 3285.62 16.95 766.38 ea68f3b
deepq
       
cron 745.27 1.93 1139.2 22.2 483.35 1010.79 -7.21 2566.6 ea68f3b

Learning Curves

X-axis: timesteps Y-axis: Reward (avg. 6 seeds)
0.0 0.2 0.4 0.6 0.8 1.0 1e7 2000 4000 BeamRider 0.0 0.2 0.4 0.6 0.8 1.0 1e7 0 200 400 Breakout 0.0 0.2 0.4 0.6 0.8 1.0 1e7 0 500 Enduro 0.0 0.2 0.4 0.6 0.8 1.0 1e7 −20 0 20 Pong 0.0 0.2 0.4 0.6 0.8 1.0 1e7 0 10000 Qbert 0.0 0.2 0.4 0.6 0.8 1.0 1e7 0 500 1000 1500 Seaquest 0.0 0.2 0.4 0.6 0.8 1.0 1e7 500 1000 1500 SpaceInvaders