Search By Subject

Learning in tightly coupled multiagent settings with sparse rewards is challenging because multiple agents must reach the goal state simultaneously for the team to receive a reward. This is even more challenging under temporal coupling constraints - ...

Evolutionary learning algorithms have been successfully applied to multiagent problems where the desired system behavior can be captured by a single fitness signal. However, the complexity of many real world applications cannot be reduced to a single ...

Multiagent teams have been shown to be effective in many domains that require coordination among team members. However, finding valuable joint-actions becomes increasingly difficult in tightly-coupled domains where each agent's performance depends on ...

In many multiagent domains, and particularly in tightly coupled domains, teasing an agent's contribution to the system performance based on a single episodic return is difficult. This well-known difficulty hits state-to-action mapping approaches such as ...

We present Modular Memory Units (MMUs), a new class of memory-augmented neural network. MMU builds on the gated neural architecture of Gated Recurrent Units (GRUs) and Long Short Term Memory (LSTMs), to incorporate an external memory block, similar to a ...

Rapid adaptation to dynamically change one's policy based on a singular observation is a complex problem. This is especially difficult in multiagent systems where the global behavior emerges from inter-agent interactions. In this paper, we introduce a ...

Distributed agents concurrently learning to coordinate in a multiagent system can suffer from considerable amounts of agent noise. This is the noise that arises from the non-stationarity of the learning environment for each individual agent since other ...

In this paper, we present a new memory-augmented neural network called Gated Recurrent Unit with Memory Block (GRU-MB). Our architecture builds on the gated neural architecture of a Gated Recurrent Unit (GRU) and integrates an external memory block, ...

Difference evaluation functions have resulted in excellent multiagent behavior in many domains, including air traffic and mobile robot control. However, calculating difference evaluation functions requires determining the value of a counterfactual ...

The Pareto Concavity Elimination Transformation (PaCcET) is a promising new development in multi-objective optimization. It transforms the objective space so that a computationally-cheap linear combination of objectives can attain (even concave) Pareto-...

One of the key difficulties in cooperative coevolutionary algorithms is solving the credit assignment problem. Given the performance of a team of agents, it is difficult to determine the effectiveness of each agent in the system. One solution to solving ...

A key difficulty in Cooperative Coevolutionary Algorithms (CCEAs) is the credit assignment problem[1]. One solution to the credit assignment problem is the difference evaluation function, which produces excellent results in many multiagent domains. ...

Difference evaluations can effectively shape agent feedback in multiagent learning systems, and have provided excellent results in a variety of domains, including air traffic control and distributed sensor network control. In addition to empirical ...

Determining the contribution of an agent to a system-level objective function (credit assignment) is a key area of research in cooperative multiagent systems. Multi-objective optimization is a growing area of research, though mostly focused on single ...

In any single agent system, exploration is a critical component of learning. It ensures that all possible actions receive some degree of attention, allowing an agent to converge to good policies. The same concept has been adopted by multiagent learning ...

Coordinating the joint-actions of agents in cooperative multiagent systems is a difficult problem in many real world domains. Learning in such multiagent systems can be slow because an agent may not only need to learn how to behave in a complex ...

Accurate simulation of the effects of integrating new technologies into a complex system is critical to the modernization of our antiquated air traffic system, where there exist many layers of interacting procedures, controls, and automation all ...

A key element in the continuing growth of air traffic is the increased use of automation. The Next Generation (Next-Gen) Air Traffic System will include automated decision support systems and satellite navigation that will let pilots know the precise ...

Learning in multiagent systems can be slow because agents must learn both how to behave in a complex environment and how to account for the actions of other agents. The inability of an agent to distinguish between the true environmental dynamics and ...

Reinforcement learning with reward shaping is a well-established but often computationally expensive approach to multiagent problems. Agent partitioning can assist in this computational complexity by treating each partition of agents as an independent ...