DeepAI AI Chat
Log In Sign Up

Comparing Reconstruction- and Contrastive-based Models for Visual Task Planning

by   Constantinos Chamzas, et al.

Learning state representations enables robotic planning directly from raw observations such as images. Most methods learn state representations by utilizing losses based on the reconstruction of the raw observations from a lower-dimensional latent space. The similarity between observations in the space of images is often assumed and used as a proxy for estimating similarity between the underlying states of the system. However, observations commonly contain task-irrelevant factors of variation which are nonetheless important for reconstruction, such as varying lighting and different camera viewpoints. In this work, we define relevant evaluation metrics and perform a thorough study of different loss functions for state representation learning. We show that models exploiting task priors, such as Siamese networks with a simple contrastive loss, outperform reconstruction-based representations in visual task planning.


page 1

page 3

page 5

page 9

page 10

page 11

page 12


Learning Invariant Representations for Reinforcement Learning without Reconstruction

We study how representation learning can accelerate reinforcement learni...

Temporal Predictive Coding For Model-Based Planning In Latent Space

High-dimensional observations are a major challenge in the application o...

Reinforcement Learning from Multiple Sensors via Joint Representations

In many scenarios, observations from more than one sensor modality are a...

Contrastive losses as generalized models of global epistasis

Fitness functions map large combinatorial spaces of biological sequences...

Learning Visual Planning Models from Partially Observed Images

There has been increasing attention on planning model learning in classi...

PALMER: Perception-Action Loop with Memory for Long-Horizon Planning

To achieve autonomy in a priori unknown real-world scenarios, agents sho...

On Contrastive Representations of Stochastic Processes

Learning representations of stochastic processes is an emerging problem ...