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

Optimal decision making with limited or no information in stochasticenvironments where multiple agents interact is a challenging topic in the realmof artificial intelligence. Reinforcement learning (RL) is a popular approachfor arriving at optimal strategies by predicating stimuli, such as the rewardfor following a strategy, on experience. RL is heavily explored in thesingle-agent context, but is a nascent concept in multiagent problems. To thisend, I propose several principled model-free and partially model-basedreinforcement learning approaches for several multiagent settings. In the realmof normative reinforcement learning, I introduce scalable extensions to MonteCarlo exploring starts for partially observable Markov Decision Processes(POMDP), dubbed MCES-P, where I expand the theory and algorithm to themultiagent setting. I first examine MCES-P with probably approximately correct(PAC) bounds in the context of multiagent setting, showing MCESP+PAC holds inthe presence of other agents. I then propose a more sample-efficientmethodology for antagonistic settings, MCESIP+PAC. For cooperative settings, Iextend MCES-P to the Multiagent POMDP, dubbed MCESMP+PAC. I then explore theuse of reinforcement learning as a methodology in searching for optima inrealistic and latent model environments. First, I explore a parameterizedQ-learning approach in modeling humans learning to reason in an uncertain,multiagent environment. Next, I propose an implementation of MCES-P, along withimage segmentation, to create an adaptive team-based reinforcement learningtechnique to positively identify the presence of phenotypically-expressed waterand pathogen stress in crop fields.

Optimal Decision-Making in Mixed-Agent Partially Observable Stochastic Environments via Reinforcement Learning