Browsing Theses by Subject "Reinforcement Learning"
Now showing items 1-9 of 9
-
An Adaptive Teachable Robot For Encouraging Teamwork
(University of Waterloo, 2021-01-26)Social robots used in education can take different roles, including tutor robots and peer robots. Peer robots (also called teachable robots) take the role of a novice in a teaching interaction while the students take the ... -
AlphaStar: Considerations and Human-like Constraints for Deep Learning Game Interfaces
(University of Waterloo, 2020-12-15)Games have historically been a fruitful area for artificial intelligence (AI) research, and StarCraft in particular has been an important grand challenge because of its strategic complexity, multi-agent dynamics, partial ... -
Deep Multi Agent Reinforcement Learning for Autonomous Driving
(University of Waterloo, 2020-04-29)Deep Learning and back-propagation have been successfully used to perform centralized training with communication protocols among multiple agents in a cooperative Multi-Agent Deep Reinforcement Learning (MARL) environment. In ... -
Generalization on Text-based Games using Structured Belief Representations
(University of Waterloo, 2020-12-23)Text-based games are complex, interactive simulations where a player is asked to process the text describing the underlying state of the world to issue textual commands for advancing in a game. Playing these games can be ... -
Obedience-based Multi-Agent Cooperation for Sequential Social Dilemmas
(University of Waterloo, 2020-05-14)We propose a mechanism for achieving cooperation and communication in Multi-Agent Reinforcement Learning (MARL) settings by intrinsically rewarding agents for obeying the commands of other agents. At every timestep, agents ... -
OppropBERT: An Extensible Graph Neural Network and BERT-style Reinforcement Learning-based Type Inference System
(University of Waterloo, 2022-12-20)Built-in type systems for statically-typed programming languages (e.g., Java) can only prevent rudimentary and domain-specific errors at compile time. They do not check for type errors in other domains, e.g., to prevent ... -
Reinforcement Learning for Determining Spread Dynamics of Spatially Spreading Processes with Emphasis on Forest Fires
(University of Waterloo, 2018-04-20)Machine learning algorithms have increased tremendously in power in recent years but have yet to be fully utilized in many ecology and sustainable resource management domains such as wildlife reserve design, forest fire ... -
Understanding and Improving SAT Solvers via Proof Complexity and Reinforcement Learning
(University of Waterloo, 2023-12-18)Despite the fact that the Boolean satisfiability (SAT) problem is NP-complete and believed to be intractable, SAT solvers are routinely used by practitioners to solve hard problems in wide variety of fields such as software ... -
Use of Slip Prediction for Learning Grasp-Stability Policies in Robotic-Grasp Simulation
(University of Waterloo, 2023-07-04)The purpose of prosthetic hands is to restore a portion of dexterity lost through upper limb amputation. However, a key capability of human grasping that is missing from most currently available prosthetic hands is the ...