Browsing by Subject "Bayesian inference"

Now showing 1 - 2 of 2

Creating an adaptive collaborative playstyle-aware companion agent
(University of the Witwatersrand, Johannesburg, 2023-09) Arendse, Lindsay John; Rosman, Benjamin
Companion characters in video games play a unique part in enriching player experience. Companion agents support the player as an ally or sidekick and would typically help the player by providing hints, resources, or even fight along-side the human player. Players often adopt a certain approach or strategy, referred to as a playstyle, whilst playing video games. Players do not only approach challenges in games differently, but also play games differently based on what they find rewarding. Companion agent characters thus have an important role to play by assisting the player in a way which aligns with their playstyle. Existing companion agent approaches fall short and adversely affect the collaborative experience when the companion agent is not able to assist the human player in a manner consistent with their playstyle. Furthermore, if the companion agent cannot assist in real time, player engagement levels are lowered since the player will need to wait for the agent to compute its action - leading to a frustrating player experience. We therefore present a framework for creating companion agents that are adaptive such that they respond in real time with actions that align with the player’s playstyle. Companion agents able to do so are what we refer to as playstyle-aware. Creating a playstyle-aware adaptive agent firstly requires a mechanism for correctly classifying or identifying the player style, before attempting to assist the player with a given task. We present a method which can enable the real time in-game playstyle classification of players. We contribute a hybrid probabilistic supervised learning framework, using Bayesian Inference informed by a K-Nearest Neighbours based likelihood, that is able to classify players in real time at every step within a given game level using only the latest player action or state observation. We empirically evaluate our hybrid classifier against existing work using MiniDungeons, a common benchmark game domain. We further evaluate our approach using real player data from the game Super Mario Bros. We out perform our comparative study and our results highlight the success of our framework in identifying playstyles in a complex human player setting. The second problem we explore is the problem of assisting the identified playstyle with a suitable action. We formally define this as the ‘Learning to Assist’ problem, where given a set of companion agent policies, we aim to determine the policy which best complements the observed playstyle. An action is complementary such that it aligns with the goal of the playstyle. We extend MiniDungeons into a two-player game called Collaborative MiniDungeons which we use to evaluate our companion agent against several comparative baselines. The results from this experiment highlights that companion agents which are able to adapt and assist different playstyles on average bring about a greater player experience when using a playstyle specific reward function as a proxy for what the players find rewarding. In this way we present an approach for creating adaptive companion agents which are playstyle-aware and able to collaborate with players in real time.
Reassessment of the Phylogeny of Basal Therapsida Using Micro-Tomography and Bayesian Phylogeny
(University of the Witwatersrand, Johannesburg, 2023) Duhamel, Alienor; Rubidge, Bruce; Benoit, Julien
This PhD research is focussed on the evolution and cranial anatomy of the earliest therapsids. The Therapsida is a paraphyletic group of land tetrapods that lived mostly during the Permian and Triassic Periods. They emerged quite suddenly in the fossil record during the middle Permian, already showing diversification into five distinct groups: Biarmosuchia, Dinocephalia, Anomodontia, Gorgonopsia and Therocephalia. A sixth group, the Cynodontia, appeared during the late Permian. Of these, the anomodonts, therocephalians, and cynodonts survived the devastating Permo-Triassic mass extinction and continued to be the dominant tetrapods during the Early and Middle Triassic Periods. Ultimately, the cynodonts would evolve into the earliest mammals. Chapter 1 introduces the scientific questions tackled in this thesis. Chapter 2 provides the necessary explanations about the material and methods used for this work. The use of CT-scanning technology allows for the detailed examination of cranial internal morphology, with the goal of incorporating inner cranial characters into a phylogenetic framework. Chapters 3 and 6 focus on the fossilisation gap at the early to middle Permian transition, which has led to debates over the timing of the early diversification of the Therapsida. In Chapter 3, the geologic position and anatomy of one of the oldest known therapsids, Raranimus dashankouensis is reviewed. The chapter concludes with a reassessment of the basal phylogenetic position of Raranimus and suggests a Roadian origin for the taxon. Chapter 6 presents a comprehensive analysis of cranial morphological characters based on the descriptions and findings from Chapters 3, 4, and 5. Using both traditional maximum parsimony and clock-based Bayesian inference of phylogeny for the first time on the Therapsida, the results suggest that therapsids originated around 280.5 million years ago and rapidly diversified into several distinct clades during the Kungurian and Roadian Epochs. The phylogenetic relationships of several taxa are reevaluated and the findings suggest that Biseridens is more closely related to the Dinocephalia and Biarmosuchia, rather than the Anomodontia. Furthermore, the results suggest that Sinophoneus may represent the basal-most dinocephalian, and that Therocephalia might be paraphyletic. Therapsids were characterised by a wide range of cranial morphologies, with the Biarmosuchia and Anomod ontia exhibiting distinct cranial features. Both groups are considered basal among therapsids. Chapter 4 of this PhD research focuses on the postnatal ontogenetic development of cranial ornamentation in Biarmosuchia and possible impact on phylogeny. The results suggests that cranial bosses and ridges are ontogenetic features and the parietal bone originates from multiple centres of ossification. Chapter 5 is a comprehensive cranial description of several basal anomodont specimens. The Chapter concludes with a review of the taxonomy of the genus Eodicynodon and proposes the creation of a new taxonomical unit for specimen NMQR 2913.