RESEARCH
Dynamics-aware Embeddings
April 25, 2020
Abstract
In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences. These embeddings capture the structure of the environment’s dynamics, enabling efficient policy learning. We demonstrate that our action embeddings alone improve the sample efficiency and peak performance of model-free RL on control from low-dimensional states. By combining state and action embeddings, we achieve efficient learning of high-quality policies on goal-conditioned continuous control from pixel observations in only 1-2 million environment steps.
AUTHORS
Publisher
International Conference on Learning Representations (ICLR)
Recent Publications
November 27, 2022
CORE MACHINE LEARNING
Neural Attentive Circuits
Nicolas Ballas, Bernhard Schölkopf, Chris Pal, Francesco Locatello, Li Erran, Martin Weiss, Nasim Rahaman, Yoshua Bengio
November 27, 2022
November 27, 2022
Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs
Andrea Tirinzoni, Aymen Al Marjani, Emilie Kaufmann
November 27, 2022
November 16, 2022
NLP
Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models
Kushal Tirumala, Aram H. Markosyan, Armen Aghajanyan, Luke Zettlemoyer
November 16, 2022
November 10, 2022
COMPUTER VISION
Learning State-Aware Visual Representations from Audible Interactions
Unnat Jain, Abhinav Gupta, Himangi Mittal, Pedro Morgado
November 10, 2022
