A lightweight attention module that weights embeddings from multiple pre-trained models achieves comparable Atari RL performance to end-to-end training, with improved robustness to visual changes.
Agent57: Outperforming the atari human benchmark
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement Learning
A lightweight attention module that weights embeddings from multiple pre-trained models achieves comparable Atari RL performance to end-to-end training, with improved robustness to visual changes.