3. Electronic Theses and Dissertations (ETDs) - All submissions
Permanent URI for this communityhttps://wiredspace.wits.ac.za/handle/10539/45
Browse
2 results
Search Results
Item Skill discovery from multiple related demonstrators(2018) Ranchod, PraveshAn important ability humans have is that we can recognise that some collec tions of actions are useful in multiple tasks, allowing us to exploit these skills. A human who can run while playing basketball does not need to relearn this ability when he is playing soccer as he can employ his previously learned run ning skill. WeextendthisideatothetaskofLearningfromDemonstration(LfD),wherein an agent must learn a task by observing the actions of a demonstrator. Tradi tional LfD algorithms learn a single task from a set of demonstrations, which limits the ability to reuse the learned behaviours. We instead recover all the latentskillsemployedinasetofdemonstrations. Thedifficultyinvolvedliesin determiningwhichcollectionsofactionsinthedemonstrationscanbegrouped together and termed “skills”? We use a number of characteristics observed in studies of skill discovery in children to guide this segmentation process – use fulness (they lead to some reward), chaining (we tend to employ certain skills in common combinations), and reusability (the same skill will be employed in many different contexts). Weusereinforcementlearningtomodelgoaldirectedbehaviour,hiddenMarkov models to model the links between skills, and nonparametric Bayesian cluster ing to model reusability in a potentially infinite set of skills. We introduce nonparametric Bayesian reward segmentation (NPBRS), an algorithm that is abletosegmentdemonstrationtrajectoriesintocomponentskills,usinginverse reinforcement learning to recover reward functions representing the skill ob i jectives. We then extend the algorithm to operate in domains with continuous state spaces for which the transition model is not specified, with the algorithm suc cessfully recovering component skills in a number of simulated domains. Fi nally, we perform an experiment on CHAMP, a physical robot tasked with mak ingvariousdrinks,anddemonstratethatthealgorithmisabletorecoveruseful skills in a robot domain.Item Parallelisation of EST clustering(2006-03-23) Ranchod, PraveshThe field of bioinformatics has been developing steadily, with computational problems related to biology taking on an increased importance as further advances are sought. The large data sets involved in problems within computational biology have dictated a search for good, fast approximations to computationally complex problems. This research aims to improve a method used to discover and understand genes, which are small subsequences of DNA. A difficulty arises because genes contain parts we know to be functional and other parts we assume are non-functional as there functions have not been determined. Isolating the functional parts requires the use of natural biological processes which perform this separation. However, these processes cannot read long sequences, forcing biologists to break a long sequence into a large number of small sequences, then reading these. This creates the computational difficulty of categorizing the short fragments according to gene membership. Expressed Sequence Tag Clustering is a technique used to facilitate the identification of expressed genes by grouping together similar fragments with the assumption that they belong to the same gene. The aim of this research was to investigate the usefulness of distributed memory parallelisation for the Expressed Sequence Tag Clustering problem. This was investigated empirically, with a distributed system tested for speed against a sequential one. It was found that distributed memory parallelisation can be very effective in this domain. The results showed a super-linear speedup for up to 100 processors, with higher numbers not tested, and likely to produce further speedups. The system was able to cluster 500000 ESTs in 641 minutes using 101 processors.