Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Procgen dataset and benchmarks · SOTA2 Research

Research Datasets

Procgen

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Reinforcement Learning

Procgen (test)

21.61BigFish Return

21

Reinforcement Learning Generalization

Procgen 16 games (train)

27.5bigfish

16

Reinforcement Learning Generalization

Procgen 16 games (test)

22.1BigFish Score

16

Interaction-limited policy learning

Procgen full distribution easy mode

36.3Bigfish Score

8

Virtual-embodiment transfer

Procgen Group G2: heist jumper miner (test)

0.563SSIM

7

Virtual-embodiment transfer

Procgen Group G1: caveflyer/chaser/ninja (test)

59.4SSIM

7

Reinforcement Learning

Procgen Maze

5.1Return

6

Reinforcement Learning

Procgen CoinRun

5.65Return

6

Reinforcement Learning

PROCGEN HEIST 1.0 (test)

98.57Accuracy (%)

6

Reinforcement Learning

PROCGEN LEAPER 1.0 (test)

57.64Accuracy

6

Reinforcement Learning

PROCGEN CHASER 1.0 (test)

62.75Accuracy

6

Reinforcement Learning

PROCGEN BIGFISH 1.0 (test)

84.13Accuracy

6

Reinforcement Learning

Procgen easy levels zero-shot generalization 16 games (test)

0.297bigfish

6

Reinforcement Learning

Procgen StarPilot 1.0 (train)

44.1Mean Train Performance

6

Reinforcement Learning

Procgen CoinRun 1.0 (train)

10Mean Train Performance

6

Reinforcement Learning

Procgen CaveFlyer 1.0 (train)

7.5Mean Performance (Train)

6

Reinforcement Learning

Procgen BigFish 1.0 (train)

20.8Mean Train Performance

6

Offline goal-conditioned RL

Procgen Maze 500 (test)

64.5Normalized Score

5

Offline goal-conditioned RL

Procgen Maze 500 (train)

82.5Normalized Score

5

Reinforcement Learning

Procgen 16 environments

89.4BigFish Score

4

Reinforcement Learning

ProcGen 1.0 (test)

20.01BigFish Score

4

Procgen easy

7.07Mean Episode Return

4

Procgen easy

5.87Mean Episode Return

4

Procgen easy

1.87Mean Episode Return

4

Procgen easy

9.2Mean Episode Return

4

Page 1 of 2

PreviousNext

Popular tasks

Reinforcement Learning Reinforcement Learning Generalization Offline goal-conditioned RL Virtual-embodiment transfer Lifelong Reinforcement Learning

Follow for updates

Join SOTA2 Contact