English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Humans are experts at high-fidelity imitation -- closely mimicking ademonstration, often in one attempt. Humans use this ability to quickly solve atask instance, and to bootstrap learning of new tasks. Achieving theseabilities in autonomous agents is an open problem. In this paper, we introducean off-policy RL algorithm (MetaMimic) to narrow this gap. MetaMimic can learnboth (i) policies for high-fidelity one-shot imitation of diverse novel skills,and (ii) policies that enable the agent to solve tasks more efficiently thanthe demonstrators. MetaMimic relies on the principle of storing all experiencesin a memory and replaying these to learn massive deep neural network policiesby off-policy RL. This paper introduces, to the best of our knowledge, thelargest existing neural networks for deep RL and shows that larger networkswith normalization are needed to achieve one-shot high-fidelity imitation on achallenging manipulation task. The results also show that both types of policycan be learned from vision, in spite of the task rewards being sparse, andwithout access to demonstrator actions.

One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL