Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ...

GRIMGEP: Learning Progress for Robust Goal Sampling in Visual Deep Reinforcement Learning

Abstract : Designing agents, capable of learning autonomously a wide range of skills is critical in order to increase the scope of reinforcement learning. It will both increase the diversity of learned skills and reduce the burden of manually designing reward functions for each skill. Self-supervised agents, setting their own goals, and trying to maximize the diversity of those goals have shown great promise towards this end. However, a currently known limitation of agents trying to maximize the diversity of sampled goals is that they tend to get attracted to noise or more generally to parts of the environments that cannot be controlled (distractors). When agents have access to predefined goal features or expert knowledge, absolute Learning Progress (ALP) provides a way to distinguish between regions that can be controlled and those that cannot. However, those methods often fall short when the agents are only provided with raw sensory inputs such as images. In this work we extend those concepts to unsupervised image-based goal exploration. We propose a framework that allows agents to autonomously identify and ignore noisy distracting regions while searching for novelty in the learnable regions to both improve overall performance and avoid catastrophic forgetting. Our framework can be combined with any stateof- the-art novelty seeking goal exploration approaches. We construct a rich 3D image based environment with distractors. Experiments on this environment show that agents using our framework successfully identify interesting regions of the environment, resulting in drastically improved performances. The source code is available at https://sites.google.com/view/grimgep.
Complete list of metadata

https://hal.inria.fr/hal-03121352
Contributor : Grgur Kovac Connect in order to contact the contributor
Submitted on : Monday, November 22, 2021 - 2:15:39 PM
Last modification on : Saturday, March 26, 2022 - 4:00:38 AM

File

GRIMGEP_arxiv.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03121352, version 2
  • ARXIV : 2008.04388

Collections

Citation

Grgur Kovač, Adrien Laversanne-Finot, Pierre-Yves Oudeyer. GRIMGEP: Learning Progress for Robust Goal Sampling in Visual Deep Reinforcement Learning. 2021. ⟨hal-03121352v2⟩

Share

Metrics

Record views

71

Files downloads

84