Efficient Intrinsically Motivated Robotic Grasping with Learning-Adaptive Imagination in Latent Space

10/10/2019
by   Muhammad Burhan Hafez, et al.
3

Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this direction inspired by human mental simulation of motor behavior. We propose a learning-adaptive imagination approach which, unlike previous approaches, takes into account the reliability of the learned dynamics model used for imagining the future. Our approach learns an ensemble of disjoint local dynamics models in latent space and derives an intrinsic reward based on learning progress, motivating the controller to take actions leading to data that improves the models. The learned models are used to generate imagined experiences, augmenting the training set of real experiences. We evaluate our approach on learning vision-based robotic grasping and show that it significantly improves sample efficiency and achieves near-optimal performance in a sparse reward environment.

READ FULL TEXT

Authors

page 1

page 5

page 6

04/19/2020

Improving Robot Dual-System Motor Learning with Intrinsically Motivated Meta-Control and Latent-Space Experience Imagination

Combining model-based and model-free learning systems has been shown to ...
05/05/2019

Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning

Recent success in deep reinforcement learning for continuous control has...
07/27/2019

Towards Model-based Reinforcement Learning for Industry-near Environments

Deep reinforcement learning has over the past few years shown great pote...
06/05/2020

Hybrid Control for Learning Motor Skills

We develop a hybrid control approach for robot learning based on combini...
05/15/2019

Reinforcement Learning for Robotics and Control with Active Uncertainty Reduction

Model-free reinforcement learning based methods such as Proximal Policy ...
06/28/2022

Dext-Gen: Dexterous Grasping in Sparse Reward Environments with Full Orientation Control

Reinforcement learning is a promising method for robotic grasping as it ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.