Pith. sign in

REVIEW

Zero Shot Learning on Simulated Robots

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1910.01994 v1 pith:NOL4KI6S submitted 2019-10-04 cs.RO cs.AIcs.LG

Zero Shot Learning on Simulated Robots

classification cs.RO cs.AIcs.LG
keywords learningself-modeltasksdataenvironmentstateactionsreal
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.