Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

BYOL-Explore: Exploration by Bootstrapped Prediction

About

We present BYOL-Explore, a conceptually simple yet general approach for curiosity-driven exploration in visually-complex environments. BYOL-Explore learns a world representation, the world dynamics, and an exploration policy all-together by optimizing a single prediction loss in the latent space with no additional auxiliary objective. We show that BYOL-Explore is effective in DM-HARD-8, a challenging partially-observable continuous-action hard-exploration benchmark with visually-rich 3-D environments. On this benchmark, we solve the majority of the tasks purely through augmenting the extrinsic reward with BYOL-Explore s intrinsic reward, whereas prior work could only get off the ground with human demonstrations. As further evidence of the generality of BYOL-Explore, we show that it achieves superhuman performance on the ten hardest exploration games in Atari while having a much simpler design than other competitive agents.

Zhaohan Daniel Guo, Shantanu Thakoor, Miruna P\^islar, Bernardo Avila Pires, Florent Altch\'e, Corentin Tallec, Alaa Saade, Daniele Calandriello, Jean-Bastien Grill, Yunhao Tang, Michal Valko, R\'emi Munos, Mohammad Gheshlaghi Azar, Bilal Piot• 2022

Related benchmarks

TaskDatasetResultRank
Reinforcement LearningAtari 2600 MONTEZUMA'S REVENGE
Score5.15e+3
45
Reinforcement LearningAtari 2600 Qbert
Score2.00e+5
15
Reinforcement LearningAtari 10 hard-exploration games (train)
Alien Score1.25e+5
10
Reinforcement LearningAtari 2600 GRAVITAR
GRAVITAR Score796
10
Reinforcement LearningAtari 2600 FREEWAY
Score12.94
9
BaseballDM-HARD-8
Max Agent Score9.94
5
Navigate CubesDM-HARD-8
Max Agent Score10
5
Reinforcement LearningAtari 10-hardest exploration games (test)
Mean CHNS100
5
Reinforcement LearningAtari 10 hard-exploration games
Alien Score1.25e+5
5
Throw AcrossDM-HARD-8
Max Agent Score8.46
5
Showing 10 of 22 rows

Other info

Follow for update