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/

Zendy Plus

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

Zendy Tools

Zendy Open

Incomplete knowledge of the environment leads an agent to make decisionsunder uncertainty. One of the major dilemmas in Reinforcement Learning (RL)where an autonomous agent has to balance two contrasting needs in making itsdecisions is: exploiting the current knowledge of the environment to maximizethe cumulative reward as well as exploring actions that allow improving theknowledge of the environment, hopefully leading to higher reward values(exploration-exploitation trade-off). Concurrently, another relevant issueregards the full observability of the states, which may not be assumed in allapplications. For instance, when 2D images are considered as input in an RLapproach used for finding the best actions within a 3D simulation environment.In this work, we address these issues by deploying and testing severaltechniques to balance exploration and exploitation trade-off on partiallyobservable systems for predicting steering wheels in autonomous drivingscenarios. More precisely, the final aim is to investigate the effects of usingboth adaptive and deterministic exploration strategies coupled with a DeepRecurrent Q-Network. Additionally, we adapted and evaluated the impact of amodified quadratic loss function to improve the learning phase of theunderlying Convolutional Recurrent Neural Network. We show that adaptivemethods better approximate the trade-off between exploration and exploitationand, in general, Softmax and Max-Boltzmann strategies outperform epsilon-greedytechniques.

Dealing with uncertainty: balancing exploration and exploitation in deep recurrent reinforcement learning