Search Constraints

Start Over
Filtering by: Creator Higgins, Christopher P. Remove constraint Creator: Higgins, Christopher P. Advisor Tumer, Kagan Remove constraint Advisor: Tumer, Kagan

Search Results

  • Multi-Reward Learning and Sparse Rewards

    Creator:
    Christopher, Reid M.
    Abstract:
    Reinforcement learning has made impressive strides in solving problems in challenging domains, but problems are increasingly being described with sparse rewards. Sparse rewards directly reduce the rate at which useful feedback is provided to the learner and make it difficult to distinguish between what specific actions led to the reception...
    Resource Type:
    Capstone Project
    Full Text:
    Multi-Reward Learning and Sparse Rewards Reid Christopher

  • Coevolution and transfer learning in a point-to-point fleet coordination problem

    Creator:
    Yliniemi, Logan Michael
    Abstract:
    In this work we present a multiagent Fleet Coordination Problem (FCP). In this formulation, agents seek to minimize the fuel consumed to complete all deliveries while maintaining acceptable on-time delivery performance. Individual vehicles must both (i) bid on the rights to deliver a load of goods from origin to destination...
    Resource Type:
    Masters Thesis
    Full Text:
    to thank Carey E. and Elizabeth P. Yliniemi for their support and guidance through the years

  • Multi-Objective Optimization in Multiagent Systems

    Creator:
    Yliniemi, Logan Michael
    Abstract:
    Cooperative multiagent systems are used as solution concepts in many application domains including air traffic control, satellite communications, and extra planetary exploration. As systems become more distributed and complex, we observe three phenomena. First, these systems cannot be accurately modeled, rendering traditional model based control methods inadequate. Second, system parameters...
    Resource Type:
    Dissertation
    Full Text:
    path. Finally, I would like to thank Carey E. and Elizabeth P. Yliniemi for their support and

  • Learning in Complex Domains : Leveraging Multiple Rewards through Alignment

    Creator:
    Klinkhammer, Eric R.
    Abstract:
    In this thesis, we introduce alignment-based algorithms for improving the performance of reinforcement learning solutions for problems where the reward signal cannot be collapsed into a single number. Many real world problems require an agent to balance performance, longevity, and safety, and do so across different timelines. The key to...
    Resource Type:
    Masters Thesis

  • Multiagent Learning via Dynamic Skill Selection

    Creator:
    Sachdeva, Enna
    Abstract:
    Multiagent coordination has many real-world applications such as self-driving cars, inventory management, search and rescue, package delivery, traffic management, warehouse management, and transportation. These tasks are generally character-ized by a global team objective that is often temporally sparse - realized only upon completing an episode. The sparsity of the shared...
    Resource Type:
    Masters Thesis
    Full Text:
    cumulative reward. The environ- ment is characterized by P (st+1|st, at), i.e the probability of next state

  • Providing Informative Feedback for Learning in Tightly Coupled Multiagent Domains

    Creator:
    Rockefeller, Golden C.
    Abstract:
    Autonomous agents that sense, decide, act, and coordinate effectively with each other are critical in many real-world domains such as autonomous driving, search and rescue missions, air traffic management, and underwater or deep space exploration. All such domains share a key difficulty: though high-level mission goals are clear to system...
    Resource Type:
    Dissertation
    Full Text:
    described as a tuple (S,A, P,R,Ω, O, γ). S in the set of possible states. A is the set of possible actions

  • Robust Long Term Autonomy Through Local Behaviors

    Creator:
    Yates, Connor L.
    Abstract:
    Multi-robot teams offer promising solutions for many long term deployments in remote and dangerous domains, such as extraterrestrial or underseas exploration. However, long term deployments present many problems preventing robot teams from operating effectively. Learning over long time scales is makes it difficult to assign credit to robots' actions, as...
    Resource Type:
    Dissertation

  • Tackling Credit Assignment Using Memory and Multilevel Optimization for Multiagent Reinforcement Learning

    Creator:
    Khadka, Shauharda
    Abstract:
    There is growing commercial interest in the use of multiagent systems in real world applications. Some examples include inventory management in warehouses, smart homes, planetary exploration, search and rescue, air-traffic management and autonomous transportation systems. However, multiagent coordination is an extremely challenging problem. First, information relevant for coordination is often...
    Resource Type:
    Dissertation

  • CLEAN learning to improve coordination and scalability in multiagent systems

    Creator:
    HolmesParker, Chris
    Abstract:
    Recent advances in multiagent learning have led to exciting new capabilities spanning fields as diverse as planetary exploration, air traffic control, military reconnaissance, and airport security. Such algorithms provide a tangible benefit over traditional control algorithms in that they allow fast responses, adapt to dynamic environments, and generally scale well....
    Resource Type:
    Dissertation
    Full Text:
    1400 1600 1800 2000 S ys te m P er fo rm an ce Episodes The Impact of Exploration on

  • Counterfactual thinking applied to multiagent systems

    Creator:
    Zerbel, Nicholas
    Abstract:
    Multiagent approaches are well suited to designing autonomous solutions for systems that feature complex interactions between many individuals such as in autonomous traffic systems and multi-robot exploration systems. However, creating autonomous agents that function effectively in these systems is a challenging task. In these complex environments, agents need informative reward...
    Resource Type:
    Dissertation
    Full Text:
    outperformed by CFL-P in the 12 agent system