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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Exploration has been one of the greatest challenges in reinforcement learning(RL), which is a large obstacle in the application of RL to robotics. Even withstate-of-the-art RL algorithms, building a well-learned agent often requirestoo many trials, mainly due to the difficulty of matching its actions withrewards in the distant future. A remedy for this is to train an agent withreal-time feedback from a human observer who immediately gives rewards for someactions. This study tackles a series of challenges for introducing such ahuman-in-the-loop RL scheme. The first contribution of this work is ourexperiments with a precisely modeled human observer: binary, delay,stochasticity, unsustainability, and natural reaction. We also propose an RLmethod called DQN-TAMER, which efficiently uses both human feedback and distantrewards. We find that DQN-TAMER agents outperform their baselines in Maze andTaxi simulated environments. Furthermore, we demonstrate a real-worldhuman-in-the-loop RL application where a camera automatically recognizes auser's facial expressions as feedback to the agent while the agent explores amaze.

DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback