Keywords: robotics, RL, representation learning
TL;DR: We propose a method that trains a neural network to compute a context-dependent basis for high dimensional actuation commands.
Abstract: Choosing an appropriate action representation is an integral part of solving robotic manipulation problems. Published approaches include latent action models which compress the control space into a low dimensional manifold. These involve training a conditional autoencoder, where the current observation and a low-dimensional action are passed through a neural network decoder to compute high dimensional actuation commands. Such models can have a large number of parameters, and can be difficult to interpret from a user perspective. In this work, we propose that similar performance gains in robotics tasks can be achieved by restructuring the neural network to map observations to a basis for a context-dependent linear actuation subspace. This results in an action interface wherein a user’s actions determine a linear combination of a state-conditioned actuation basis. We introduce the Neural Householder Transform (NHT) as a method for computing this basis. Our results show that reinforcement learning agents trained with NHT in kinematic manipulation and locomotion environments tend to be more robust to hyperparameter choice and achieve higher final success rates compared to agents trained with alternative action representations. NHT agents outperformed agents trained with joint velocity/torque actions, agents trained with an SVD actuation basis, and agents trained with a LASER action interface in the WAMWipe, WAMGrasp, and HalfCheetah environments.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning