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/Reactor 500M

Reactor 500M

Reported on 40 benchmarks across 2 tasks · 1 paper · 8 SOTA

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

Playing Games40 results

  • Atari GamesonAtari 2600 Crazy Climber
    Score· 2017-04-15
    236422
    best: 565909.85 (Agent57)
    SOTA
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Alien
    Score· 2017-04-15
    12689.1
    best: 741812.63 (MuZero)
    SOTA
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Chopper Command
    Score· 2017-04-15
    107779
    best: 999999 (GDI-H3)
    SOTA
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Defender
    Score· 2017-04-15
    223025
    best: 993010 (CGP)
    SOTA
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Crazy Climber
    Score· 2017-04-15
    236422
    best: 565909.85 (Agent57)
    SOTA
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Alien
    Score· 2017-04-15
    12689.1
    best: 741812.63 (MuZero)
    SOTA
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Chopper Command
    Score· 2017-04-15
    107779
    best: 999999 (GDI-H3)
    SOTA
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Defender
    Score· 2017-04-15
    223025
    best: 993010 (CGP)
    SOTA
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Boxing
    Score· 2017-04-15
    99.4
    best: 100 (MuZero)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Double Dunk
    Score· 2017-04-15
    23
    best: 24 (UCT)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Centipede
    Score· 2017-04-15
    3422
    best: 1422628 (Go-Explore)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Enduro
    Score· 2017-04-15
    2224.2
    best: 14330 (GDI-I3)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Breakout
    Score· 2017-04-15
    514.8
    best: 864 (GDI-H3(200M frames))
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Amidar
    Score· 2017-04-15
    1015.8
    best: 29660.08 (Agent57)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Asteroids
    Score· 2017-04-15
    3726.1
    best: 760005 (GDI-H3)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Demon Attack
    Score· 2017-04-15
    115154
    best: 787985 (GDI-H3)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Battle Zone
    Score· 2017-04-15
    64070
    best: 934134.88 (Agent57)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Beam Rider
    Score· 2017-04-15
    11033.4
    best: 454993.53 (MuZero)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Asterix
    Score· 2017-04-15
    205914
    best: 999999 (GDI-H3)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Bowling
    Score· 2017-04-15
    81
    best: 260.13 (MuZero)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Assault
    Score· 2017-04-15
    8323.3
    best: 143972.03 (MuZero)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Berzerk
    Score· 2017-04-15
    2303.1
    best: 197376 (Go-Explore)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Atlantis
    Score· 2017-04-15
    302831
    best: 3837300 (GDI-H3)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Atari GamesonAtari 2600 Bank Heist
    Score· 2017-04-15
    1259.7
    best: 27219.8 (MuZero (Res2 Adam))
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Boxing
    Score· 2017-04-15
    99.4
    best: 100 (MuZero)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Double Dunk
    Score· 2017-04-15
    23
    best: 24 (UCT)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Centipede
    Score· 2017-04-15
    3422
    best: 1422628 (Go-Explore)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Enduro
    Score· 2017-04-15
    2224.2
    best: 14330 (GDI-I3)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Breakout
    Score· 2017-04-15
    514.8
    best: 864 (GDI-H3(200M frames))
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Amidar
    Score· 2017-04-15
    1015.8
    best: 29660.08 (Agent57)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Asteroids
    Score· 2017-04-15
    3726.1
    best: 760005 (GDI-H3)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Demon Attack
    Score· 2017-04-15
    115154
    best: 787985 (GDI-H3)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Battle Zone
    Score· 2017-04-15
    64070
    best: 934134.88 (Agent57)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Beam Rider
    Score· 2017-04-15
    11033.4
    best: 454993.53 (MuZero)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Asterix
    Score· 2017-04-15
    205914
    best: 999999 (GDI-H3)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Bowling
    Score· 2017-04-15
    81
    best: 260.13 (MuZero)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Assault
    Score· 2017-04-15
    8323.3
    best: 143972.03 (MuZero)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Berzerk
    Score· 2017-04-15
    2303.1
    best: 197376 (Go-Explore)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Atlantis
    Score· 2017-04-15
    302831
    best: 3837300 (GDI-H3)
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651
  • Video GamesonAtari 2600 Bank Heist
    Score· 2017-04-15
    1259.7
    best: 27219.8 (MuZero (Res2 Adam))
    The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement LearningarXiv:1704.04651