CRC-RL：教師なし強化学習のための新規視覚特徴表現アーキテクチャ
CRC-RL: A Novel Visual Feature Representation Architecture for Unsupervised Reinforcement Learning
視覚特徴表現学習を改善するため、コントラスティブ・再構成・一貫性損失を組み合わせたCRC損失とSiamese Twinエンコーダを用いるCRC-RLを提案し、DeepMind制御スイートで最先端性能を達成した。
著者: Darshita Jain, Anima Majumder, Samrat Dutta, Swagat Kumar
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
This paper addresses the problem of visual feature representation learning with an aim to improve the performance of end-to-end reinforcement learning (RL) models. Specifically, a novel architecture is proposed that uses a heterogeneous loss function, called CRC loss, to learn improved visual features which can then be used for policy learning in RL. The CRC-loss function is a combination of three individual loss functions, namely, contrastive, reconstruction and consistency loss. The feature representation is learned in parallel to the policy learning while sharing the weight updates through a Siamese Twin encoder model. This encoder model is augmented with a decoder network and a feature projection network to facilitate computation of the above loss components. Through empirical analysis involving latent feature visualization, an attempt is made to provide an insight into the role played by this loss function in learning new action-dependent features and how they are linked to the complexity of the problems being solved. The proposed architecture, called CRC-RL, is shown to outperform the existing state-of-the-art methods on the challenging Deep mind control suite environments by a significant margin thereby creating a new benchmark in this field.
