Search Constraints

Start Over
Filtering by: Creator Congalton, Russell G. Remove constraint Creator: Congalton, Russell G. Contributor advisor sim Tumer, Kagan Remove constraint Contributor advisor sim: Tumer, Kagan

Search Results

  • Reinforcement learning-based off-equilibrium incentives to approximate the VCG mechanism

    Creator:
    Moissinac, Béatrice
    Abstract:
    Auctions are used to solve resource allocation problem between many agents and many items in real-world settings. Unfortunately, in most cases, it is possible for selfish agents to manipulate the system for their own interest at the expense of the social welfare. Such manipulation can be prevented using the Vickrey-Clarke-Groves...
    Resource Type:
    Masters Thesis
    Full Text:
    system objective is the sum of the individual valuations after the game is played. G(geff (Θ̂)) = ∑ i∈N

  • D₊₊ : Structural Credit Assignment in Tightly Coupled Multiagent Domains

    Creator:
    Rahmattalabi, Aida
    Abstract:
    Autonomous multiagent teams can be used in complex exploration tasks to both expedite the exploration and improve the efficiency. However, use of multiagent systems presents additional challenges. Specifically, in domains where the agents' actions are tightly coupled, coordinating multiple agents to achieve cooperative behavior at the group level is difficult....
    Resource Type:
    Masters Thesis
    Full Text:
    observations to be made to account as success. . . . 25 4.2 Observation performance of policies trained on G

  • Distortion of Agent States for Improved Coordination

    Creator:
    Yates, Connor L
    Abstract:
    Many real world problems have partial solutions or intermediary steps which can lead toward solving the problem. When assembling robotic teams to solve these problems, we have intuition about which intermediary steps are more useful than others. We examine methods to identify and apply our designer intuition onto tightly coupled...
    Resource Type:
    Honors College Thesis
    Full Text:
    quickly that what it is doing is correct. The global reward (G), and the difference reward (D) can be

  • 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
    Full Text:
    this specific order, starting at the first node (G = 0). All parent nodes must be observed before each

  • 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:
    fitness eval- uation: G, the global system utility (upper, dotted line); L i (lower, solid line). Note

  • Combining coordination mechanisms to improve performance in multi-robot teams

    Creator:
    Nasroullahi, Ehsan
    Abstract:
    Coordination is essential to achieving good performance in cooperative multiagent systems. To date, most work has focused on either implicit or explicit coordination mechanisms, while relatively little work has focused on the benefits of combining these two approaches. In this work we demonstrate that combining explicit and implicit mechanisms can...
    Resource Type:
    Masters Thesis
    Full Text:
    Page 5.5 Investigating the scalability of evaluation functions (G and D), com- bination of evaluation

  • 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:
    % exploration. As seen, agents using G and D experience significant decreases between their on­ line and

  • Learning-based control and coordination of autonomous UAVs

    Creator:
    Bell, Adam R.
    Abstract:
    Uninhabited aerial vehicles, also called UAVs are currently controller by a combination of a human pilot at a remote location, and autopilot systems similar to those found on commercial aircraft. As UAVs transition from remote piloting to fully autonomous operation, control laws must be developed for the tasks to be...
    Resource Type:
    Masters Thesis
    Full Text:
    over time for 3 agents where agents are rewarded using G, D, L, or a random policy is used. We see that

  • 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

  • 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:
    from training conditions, G, D, and D++ performance degrades rapidly. Using CKI, agents are provided