Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/Discrete Latent Space World Model (VQ-VAE)

Discrete Latent Space World Model (VQ-VAE)

Reported on 12 benchmarks across 2 tasks · 1 paper

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

Playing Games12 results

Atari GamesonAtari 2600 Freeway
Score· 2020-10-12
29
best: 34 (TRPO-hash)
Smaller World Models for Reinforcement Learning arXiv:2010.05767
Atari GamesonAtari 2600 Pong
Score· 2020-10-12
20.2
best: 21 (Duel noop)
Smaller World Models for Reinforcement Learning arXiv:2010.05767
Atari GamesonAtari 2600 Breakout
Score· 2020-10-12
11.6
best: 864 (GDI-H3(200M frames))
Smaller World Models for Reinforcement Learning arXiv:2010.05767
Atari GamesonAtari 2600 Crazy Climber
Score· 2020-10-12
59609.4
best: 565909.85 (Agent57)
Smaller World Models for Reinforcement Learning arXiv:2010.05767
Atari GamesonAtari 2600 Seaquest
Score· 2020-10-12
635
best: 1000000 (GDI-H3(200M frames))
Smaller World Models for Reinforcement Learning arXiv:2010.05767
Atari GamesonAtari 2600 Bank Heist
Score· 2020-10-12
121.6
best: 27219.8 (MuZero (Res2 Adam))
Smaller World Models for Reinforcement Learning arXiv:2010.05767
Video GamesonAtari 2600 Freeway
Score· 2020-10-12
29
best: 34 (TRPO-hash)
Smaller World Models for Reinforcement Learning arXiv:2010.05767
Video GamesonAtari 2600 Pong
Score· 2020-10-12
20.2
best: 21 (Duel noop)
Smaller World Models for Reinforcement Learning arXiv:2010.05767
Video GamesonAtari 2600 Breakout
Score· 2020-10-12
11.6
best: 864 (GDI-H3(200M frames))
Smaller World Models for Reinforcement Learning arXiv:2010.05767
Video GamesonAtari 2600 Crazy Climber
Score· 2020-10-12
59609.4
best: 565909.85 (Agent57)
Smaller World Models for Reinforcement Learning arXiv:2010.05767
Video GamesonAtari 2600 Seaquest
Score· 2020-10-12
635
best: 1000000 (GDI-H3(200M frames))
Smaller World Models for Reinforcement Learning arXiv:2010.05767
Video GamesonAtari 2600 Bank Heist
Score· 2020-10-12
121.6
best: 27219.8 (MuZero (Res2 Adam))
Smaller World Models for Reinforcement Learning arXiv:2010.05767