Learning Task-Relevant Representations with Selective Contrast for Reinforcement Learning in a Real-World Application

2021-06-13 · ICML Workshop URL 2021 7 · Flemming Brieger, Daniel Alexander Braun, Sascha Lange

We use contrastive learning to obtain task-relevant state-representations from images for reinforcement learning in a real-world system. To test the quality of the representations, an agent is trained with reinforcement learning in the Neuro-Slot-Car environment (Kietzmann & Riedmiller, 2009; Lange et al., 2012). In our experiments, we restrict the distribution from which samples are drawn for comparison in the contrastive loss. Our results show, that the choice of sampling distribution for negative samples is essential to allow task-relevant features to be represented in the presence of more prevalent, but irrelevant features. This adds to recent research on feature suppression and feature invariance in contrastive representation learning. With the training of the reinforcement learning agent, we present to our knowledge a first approach of using contrastive learning of state-representations for control in a real-world environment, using only images from one static camera.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Representation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

HCSC: Hierarchical Contrastive Selective Coding

2022-02-01 · CVPR 2022 1 · Yuanfan Guo, Minghao Xu, Jiawen Li, Bingbing Ni 외

Hierarchical semantic structures naturally exist in an image dataset, in which several semantically relevant image clusters can be further integrated into a larger cluster with coarser-grained semantics. Capturing such s…

Contrastive Learning Representation Learning

Deep Reinforcement Learning via Object-Centric Attention

2025-04-03 · Jannis Blüml, Cedric Derstroff, Bjarne Gregori, Elisabeth Dillies 외

Deep reinforcement learning agents, trained on raw pixel inputs, often fail to generalize beyond their training environments, relying on spurious correlations and irrelevant background details. To address this issue, obj…

Deep Reinforcement Learning Inductive Bias Object reinforcement-learning+1

On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning

2021-05-04 · ICLR 2022 4 · Marc Aurel Vischer, Robert Tjarko Lange, Henning Sprekeler

The lottery ticket hypothesis questions the role of overparameterization in supervised deep learning. But how is the performance of winning lottery tickets affected by the distributional shift inherent to reinforcement l…

Behavioural cloning Deep Reinforcement Learning Imitation Learning Inductive Bias+4

Contrastive Learning from Demonstrations

2022-01-30 · André Correia, Luís A. Alexandre

This paper presents a framework for learning visual representations from unlabeled video demonstrations captured from multiple viewpoints. We show that these representations are applicable for imitating several robotic t…

Contrastive Learning reinforcement-learning Reinforcement Learning (RL)Self-Supervised Learning+1

RenyiCL: Contrastive Representation Learning with Skew Renyi Divergence

2022-08-12 · Kyungmin Lee, Jinwoo Shin

Contrastive representation learning seeks to acquire useful representations by estimating the shared information between multiple views of data. Here, the choice of data augmentation is sensitive to the quality of learne…

Contrastive Learning Data Augmentation Representation Learning