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

We propose Deep Q-Networks (DQN) with model-based exploration, an algorithmcombining both model-free and model-based approaches that explores better andlearns environments with sparse rewards more efficiently. DQN is ageneral-purpose, model-free algorithm and has been proven to perform well in avariety of tasks including Atari 2600 games since it's first proposed by Minhet el. However, like many other reinforcement learning (RL) algorithms, DQNsuffers from poor sample efficiency when rewards are sparse in an environment.As a result, most of the transitions stored in the replay memory have noinformative reward signal, and provide limited value to the convergence andtraining of the Q-Network. However, one insight is that these transitions canbe used to learn the dynamics of the environment as a supervised learningproblem. The transitions also provide information of the distribution ofvisited states. Our algorithm utilizes these two observations to perform aone-step planning during exploration to pick an action that leads to statesleast likely to be seen, thus improving the performance of exploration. Wedemonstrate our agent's performance in two classic environments with sparserewards in OpenAI gym: Mountain Car and Lunar Lander.

DQN with model-based exploration: efficient learning on environments with sparse rewards