Timezone: »
In this work we consider partially observable environments with sparse rewards. We present a self-supervised representation learning method for image-based observations, which arranges embeddings respecting temporal distance of observations. This representation is empirically robust to stochasticity and suitable for novelty detection from the error of a predictive forward model. We consider episodic and life-long uncertainties to guide the exploration. We propose to estimate the missing information about the environment with the world model, which operates in the learned latent space. As a motivation of the method, we analyse the exploration problem in a tabular Partially Observable Labyrinth. We demonstrate the method on image-based hard exploration environments from the Atari benchmark and report significant improvement with respect to prior work. The source code of the method and all the experiments is available at https://github.com/htdt/lwm.
Author Information
Aleksandr Ermolov (University of Trento)
Nicu Sebe (University of Trento)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Poster: Latent World Models For Intrinsically Motivated Exploration »
Thu. Dec 10th 05:00 -- 07:00 PM Room Poster Session 5 #1502
More from the Same Authors
-
2021 Poster: Efficient Training of Visual Transformers with Small Datasets »
Yahui Liu · Enver Sangineto · Wei Bi · Nicu Sebe · Bruno Lepri · Marco Nadai -
2019 Poster: First Order Motion Model for Image Animation »
Aliaksandr Siarohin · Stéphane Lathuilière · Sergey Tulyakov · Elisa Ricci · Nicu Sebe