Browsing Atlantic Technological University (Galway-Mayo) by Author "Mannion, Patrick"
Now showing items 1-9 of 9
-
Analysing the Effects of Reward Shaping in Multi-Objective Stochastic Games
Mannion, Patrick; Duggan, Jim; Howley, Enda (2017-05)The majority ofMulti-Agent Reinforcement Learning (MARL) implementations aim to optimise systems with respect to a single objective, despite the fact that many real world problems are inherently multi-objective in nature. ... -
Curriculum Learning for Tightly Coupled Multiagent Systems
Mannion, Patrick; Rockefeller, Golden; Turner, Kagan (2019)In this paper,we leverage curriculum learning(CL) to improve the performance of multiagent systems(MAS) that are trained with the cooperative coevolution of artificial neural networks. We design curricula to progressively ... -
Equilibria in Multi-Objective Games: a Utility-Based Perspective
Mannion, Patrick; Rădulescu, Roxana; Roijers, Diederik M.; Nowé, Ann (Adaptive and Learning Agents Workshop, 2019)In multi-objective multi-agent systems (MOMAS), agents explicitly consider the possible tradeoffs between conflicting objective functions. We argue that compromises between competing objectives in MOMAS should be analysed ... -
Exploring applications of deep reinforcement learning for real-world autonomous driving systems
Mannion, Patrick; Talpaert, Victor; Sobh, Ibrahim; Kiran, Bangalore Ravi; Yogamani, Senthil; El-Sallab, Ahmad; Perez, Patrick (2019-01)Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind’s AlphaGo. It has been successfully deployed in commercial vehicles like Mobileye’s path ... -
Multi-Agent Credit Assignment in Stochastic Resource Management Games
Mannion, Patrick; Devlin, Sam; Duggan, Jim; Howley, Enda (2017-08)Multi-Agent Systems (MAS) are a form of distributed intelligence, where multiple autonomous agents act in a common environment. Numerous complex, real world systems have been successfully optimised using Multi-Agent ... -
Policy Invariance under Reward Transformations for Multi-Objective Reinforcement Learning
Mannion, Patrick; Devlin, Sam; Mason, Karl; Duggan, Jim (2017)Reinforcement Learning (RL) is a powerful and well-studied Machine Learning paradigm, where an agent learns to improve its performance in an environment by maximising a reward signal. In multi-objective Reinforcement Learning ... -
Potential-Based Reward Shaping Preserves Pareto Optimal Policies
Mannion, Patrick; Devlin, Sam; Karl, Mannion; Duggan, Jim (2017-05)Reward shaping is a well-established family of techniques that have been successfully used to improve the performance and learning speed of Reinforcement Learning agents in singleobjective problems. Here we extend the ... -
A Theoretical and Empirical Analysis of Reward Transformations in Multi-Objective Stochastic Games
Mannion, Patrick; Duggan, Jim; Howley, Enda (2017)Reward shaping has been proposed as a means to address the credit assignment problem in Multi-Agent Systems (MAS). Two popular shaping methods are Potential-Based Reward Shaping and di erence rewards, and both have been ... -
Vulnerable road user detection: state-of-the-art and open challenges
Mannion, Patrick (2019)Correctly identifying vulnerable road users (VRUs), e.g. cyclists and pedestrians, remains one of the most challenging environment perception tasks for autonomous vehicles (AVs). This work surveys the current state-of-the-art ...