DeepAI AI Chat
Log In Sign Up

Zero Shot Learning on Simulated Robots

by   Robert Kwiatkowski, et al.
Columbia University

In this work we present a method for leveraging data from one source to learn how to do multiple new tasks. Task transfer is achieved using a self-model that encapsulates the dynamics of a system and serves as an environment for reinforcement learning. To study this approach, we train a self-models on various robot morphologies, using randomly sampled actions. Using a self-model, an initial state and corresponding actions, we can predict the next state. This predictive self-model is then used by a standard reinforcement learning algorithm to accomplish tasks without ever seeing a state from the "real" environment. These trained policies allow the robots to successfully achieve their goals in the "real" environment. We demonstrate that not only is training on the self-model far more data efficient than learning even a single task, but also that it allows for learning new tasks without necessitating any additional data collection, essentially allowing zero-shot learning of new tasks.


One Model to Rule them All: Towards Zero-Shot Learning for Databases

In this paper, we present our vision of so called zero-shot learning for...

Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment

Reinforcement learning from large-scale offline datasets provides us wit...

Self-Adapting Goals Allow Transfer of Predictive Models to New Tasks

A long-standing challenge in Reinforcement Learning is enabling agents t...

One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay

Recently, model-free reinforcement learning algorithms have been shown t...

Learning Robust and Adaptive Real-World Continuous Control Using Simulation and Transfer Learning

We use model-free reinforcement learning, extensive simulation, and tran...

Know Thyself: Transferable Visuomotor Control Through Robot-Awareness

Training visuomotor robot controllers from scratch on a new robot typica...

A Zero-Shot Learning application in Deep Drawing process using Hyper-Process Model

One of the consequences of passing from mass production to mass customiz...