TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MuZero (Res2 Adam)

MuZero (Res2 Adam)

Reported on 114 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Playing Games114 results

  • Atari GamesonAtari 2600 Bank Heist
    Score· 2021-04-13
    27219.8
    SOTA
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Bank Heist
    Score· 2021-04-13
    27219.8
    SOTA
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Boxing
    Score· 2021-04-13
    100
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Skiing
    Score· uses extra data· 2021-04-13
    -30000
    best: 0 (Best Learner)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Double Dunk
    Score· 2021-04-13
    23.91
    best: 24 (UCT)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Ms. Pacman
    Score· 2021-04-13
    70659.76
    best: 243401.1 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Centipede
    Score· 2021-04-13
    874301.64
    best: 1422628 (Go-Explore)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Tutankham
    Score· 2021-04-13
    347.99
    best: 2354.91 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Freeway
    Score· 2021-04-13
    33.87
    best: 34 (TRPO-hash)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Pong
    Score· 2021-04-13
    20.95
    best: 21 (Duel noop)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Enduro
    Score· 2021-04-13
    2365.81
    best: 14330 (GDI-I3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Krull
    Score· 2021-04-13
    72570.5
    best: 594540 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Breakout
    Score· 2021-04-13
    758.04
    best: 864 (GDI-H3(200M frames))
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Frostbite
    Score· 2021-04-13
    374769.76
    best: 631378.53 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Yars Revenge
    Score· 2021-04-13
    219838.09
    best: 998532.37 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Montezuma's Revenge
    Score· 2021-04-13
    2500
    best: 43791 (Go-Explore)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Gopher
    Score· 2021-04-13
    122882.5
    best: 488830 (GDI-I3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Space Invaders
    Score· 2021-04-13
    3645.63
    best: 154380 (GDI-H3(200M frames))
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 James Bond
    Score· 2021-04-13
    28626.23
    best: 620780 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Amidar
    Score· 2021-04-13
    1197.38
    best: 29660.08 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Crazy Climber
    Score· 2021-04-13
    158541.58
    best: 565909.85 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Asteroids
    Score· 2021-04-13
    476412
    best: 760005 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Gravitar
    Score· 2021-04-13
    8006.93
    best: 19213.96 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Time Pilot
    Score· 2021-04-13
    424011.16
    best: 476763.9 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Demon Attack
    Score· 2021-04-13
    143838.04
    best: 787985 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Battle Zone
    Score· 2021-04-13
    178716.9
    best: 934134.88 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Phoenix
    Score· 2021-04-13
    815728.7
    best: 959580 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Beam Rider
    Score· 2021-04-13
    333077.44
    best: 454993.53 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Asterix
    Score· 2021-04-13
    862406.65
    best: 999999 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Kung-Fu Master
    Score· 2021-04-13
    116726.96
    best: 1666665 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Bowling
    Score· 2021-04-13
    131.65
    best: 260.13 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Kangaroo
    Score· 2021-04-13
    13838
    best: 24034.16 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Assault
    Score· 2021-04-13
    33292.22
    best: 143972.03 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Alien
    Score· 2021-04-13
    70192.35
    best: 741812.63 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Fishing Derby
    Score· 2021-04-13
    73.94
    best: 91.16 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Seaquest
    Score· 2021-04-13
    999659.18
    best: 1000000 (GDI-H3(200M frames))
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Chopper Command
    Score· 2021-04-13
    5989.55
    best: 999999 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Solaris
    Score· 2021-04-13
    5132.95
    best: 44199.93 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Surround
    Score· 2021-04-13
    9.9
    best: 10 (NoisyNet-Dueling)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Video Pinball
    Score· 2021-04-13
    865543.44
    best: 999383.2 (R2D2)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Wizard of Wor
    Score· 2021-04-13
    100096.6
    best: 197126 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Zaxxon
    Score· 2021-04-13
    154131.86
    best: 725853.9 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Defender
    Score· 2021-04-13
    557200.75
    best: 993010 (CGP)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Robotank
    Score· 2021-04-13
    100.59
    best: 131.13 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Name This Game
    Score· 2021-04-13
    101197.71
    best: 157177.85 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Star Gunner
    Score· 2021-04-13
    154548.26
    best: 839573.53 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Ice Hockey
    Score· 2021-04-13
    41.66
    best: 481.9 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Berzerk
    Score· 2021-04-13
    2705.82
    best: 197376 (Go-Explore)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Atlantis
    Score· 2021-04-13
    1137475.12
    best: 3837300 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 HERO
    Score· 2021-04-13
    37234.31
    best: 114736.26 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Venture
    Score· 2021-04-13
    1731.47
    best: 2623.71 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Private Eye
    Score· 2021-04-13
    100
    best: 95756 (Go-Explore)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Q*Bert
    Score· 2021-04-13
    94906.25
    best: 580328.14 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 River Raid
    Score· 2021-04-13
    171673.78
    best: 323417.18 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Road Runner
    Score· 2021-04-13
    531097
    best: 999999 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Up and Down
    Score· 2021-04-13
    634898.18
    best: 986440 (GDI-I3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Boxing
    Score· 2021-04-13
    100
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Skiing
    Score· uses extra data· 2021-04-13
    -30000
    best: 0 (Best Learner)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Double Dunk
    Score· 2021-04-13
    23.91
    best: 24 (UCT)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Ms. Pacman
    Score· 2021-04-13
    70659.76
    best: 243401.1 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Centipede
    Score· 2021-04-13
    874301.64
    best: 1422628 (Go-Explore)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Tutankham
    Score· 2021-04-13
    347.99
    best: 2354.91 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Freeway
    Score· 2021-04-13
    33.87
    best: 34 (TRPO-hash)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Pong
    Score· 2021-04-13
    20.95
    best: 21 (Duel noop)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Enduro
    Score· 2021-04-13
    2365.81
    best: 14330 (GDI-I3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Krull
    Score· 2021-04-13
    72570.5
    best: 594540 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Breakout
    Score· 2021-04-13
    758.04
    best: 864 (GDI-H3(200M frames))
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Frostbite
    Score· 2021-04-13
    374769.76
    best: 631378.53 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Yars Revenge
    Score· 2021-04-13
    219838.09
    best: 998532.37 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Montezuma's Revenge
    Score· 2021-04-13
    2500
    best: 43791 (Go-Explore)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Gopher
    Score· 2021-04-13
    122882.5
    best: 488830 (GDI-I3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Space Invaders
    Score· 2021-04-13
    3645.63
    best: 154380 (GDI-H3(200M frames))
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 James Bond
    Score· 2021-04-13
    28626.23
    best: 620780 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Amidar
    Score· 2021-04-13
    1197.38
    best: 29660.08 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Crazy Climber
    Score· 2021-04-13
    158541.58
    best: 565909.85 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Asteroids
    Score· 2021-04-13
    476412
    best: 760005 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Gravitar
    Score· 2021-04-13
    8006.93
    best: 19213.96 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Time Pilot
    Score· 2021-04-13
    424011.16
    best: 476763.9 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Demon Attack
    Score· 2021-04-13
    143838.04
    best: 787985 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Battle Zone
    Score· 2021-04-13
    178716.9
    best: 934134.88 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Phoenix
    Score· 2021-04-13
    815728.7
    best: 959580 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Beam Rider
    Score· 2021-04-13
    333077.44
    best: 454993.53 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Asterix
    Score· 2021-04-13
    862406.65
    best: 999999 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Kung-Fu Master
    Score· 2021-04-13
    116726.96
    best: 1666665 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Bowling
    Score· 2021-04-13
    131.65
    best: 260.13 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Kangaroo
    Score· 2021-04-13
    13838
    best: 24034.16 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Assault
    Score· 2021-04-13
    33292.22
    best: 143972.03 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Alien
    Score· 2021-04-13
    70192.35
    best: 741812.63 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Fishing Derby
    Score· 2021-04-13
    73.94
    best: 91.16 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Seaquest
    Score· 2021-04-13
    999659.18
    best: 1000000 (GDI-H3(200M frames))
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Chopper Command
    Score· 2021-04-13
    5989.55
    best: 999999 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Solaris
    Score· 2021-04-13
    5132.95
    best: 44199.93 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Surround
    Score· 2021-04-13
    9.9
    best: 10 (NoisyNet-Dueling)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Video Pinball
    Score· 2021-04-13
    865543.44
    best: 999383.2 (R2D2)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Wizard of Wor
    Score· 2021-04-13
    100096.6
    best: 197126 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Zaxxon
    Score· 2021-04-13
    154131.86
    best: 725853.9 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Defender
    Score· 2021-04-13
    557200.75
    best: 993010 (CGP)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Robotank
    Score· 2021-04-13
    100.59
    best: 131.13 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Name This Game
    Score· 2021-04-13
    101197.71
    best: 157177.85 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Star Gunner
    Score· 2021-04-13
    154548.26
    best: 839573.53 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Ice Hockey
    Score· 2021-04-13
    41.66
    best: 481.9 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Berzerk
    Score· 2021-04-13
    2705.82
    best: 197376 (Go-Explore)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Atlantis
    Score· 2021-04-13
    1137475.12
    best: 3837300 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 HERO
    Score· 2021-04-13
    37234.31
    best: 114736.26 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Venture
    Score· 2021-04-13
    1731.47
    best: 2623.71 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Private Eye
    Score· 2021-04-13
    100
    best: 95756 (Go-Explore)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Q*Bert
    Score· 2021-04-13
    94906.25
    best: 580328.14 (Agent57)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 River Raid
    Score· 2021-04-13
    171673.78
    best: 323417.18 (MuZero)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Road Runner
    Score· 2021-04-13
    531097
    best: 999999 (GDI-H3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Video GamesonAtari 2600 Up and Down
    Score· 2021-04-13
    634898.18
    best: 986440 (GDI-I3)
    Online and Offline Reinforcement Learning by Planning with a Learned ModelarXiv:2104.06294
  • Atari GamesonAtari 2600 Tennis
    Score
    0
    best: 24 (GDI-I3)
  • Atari GamesonAtari 2600 Pitfall!
    Score
    0
    best: 102571 (Go-Explore)
  • Video GamesonAtari 2600 Tennis
    Score
    0
    best: 24 (GDI-I3)
  • Video GamesonAtari 2600 Pitfall!
    Score
    0
    best: 102571 (Go-Explore)