Recurrent Independent Mechanisms

ICLR 2020 Anonymous

Learning modular structures which reflect the dynamics of the environment can lead to better generalization and robustness to changes which only affect a few of the underlying causes. We propose Recurrent Independent Mechanisms (RIMs), a new recurrent architecture in which multiple groups of recurrent cells operate with nearly independent transition dynamics, communicate only sparingly through the bottleneck of attention, and are only updated at time steps where they are most relevant... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Atari Games Atari 2600 Asterix RIMs-PPO Score 21040 # 18
Atari Games Atari 2600 Beam Rider RIMs-PPO Score 5320 # 31
Atari Games Atari 2600 Demon Attack RIMs-PPO Score 230324 # 1
Atari Games Atari 2600 Star Gunner RIMs-PPO Score 70000 # 15
Atari Games Atari 2600 Up and Down RIMs-PPO Score 390000 # 4
Atari Games Atari 2600 Zaxxon RIMs-PPO Score 15000 # 9

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet