Dynamics-aware Embeddings

08/25/2019
by   William Whitney, et al.
NYU college
5

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 actions. 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.

READ FULL TEXT

page 13

page 15

06/04/2023

For SALE: State-Action Representation Learning for Deep Reinforcement Learning

In the field of reinforcement learning (RL), representation learning is ...
06/22/2023

TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning

Despite recent progress in reinforcement learning (RL) from raw pixel da...
09/18/2022

Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective

While reinforcement learning (RL) methods that learn an internal model o...
06/06/2022

Mapping Visual Themes among Authentic and Coordinated Memes

What distinguishes authentic memes from those created by state actors? I...
06/08/2021

PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning

Learning good feature representations is important for deep reinforcemen...
04/30/2020

Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

Learning a good representation is an essential component for deep reinfo...
07/14/2020

Goal-Aware Prediction: Learning to Model What Matters

Learned dynamics models combined with both planning and policy learning ...

Code Repositories

dynamics-aware-embeddings

Official implementation of DynE, Dynamics-aware Embeddings for RL


view repo

Please sign up or login with your details

Forgot password? Click here to reset