Derrik E. Asher
YOU?
Author Swipe
View article: QuasiNav: Asymmetric Cost-Aware Navigation Planning with Constrained Quasimetric Reinforcement Learning
QuasiNav: Asymmetric Cost-Aware Navigation Planning with Constrained Quasimetric Reinforcement Learning Open
Autonomous navigation in unstructured outdoor environments is inherently challenging due to the presence of asymmetric traversal costs, such as varying energy expenditures for uphill versus downhill movement. Traditional reinforcement lear…
View article: Multi-Agent Synchronization Tasks
Multi-Agent Synchronization Tasks Open
In multi-agent reinforcement learning (MARL), coordination plays a crucial role in enhancing agents' performance beyond what they could achieve through cooperation alone. The interdependence of agents' actions, coupled with the need for co…
View article: CoverNav: Cover Following Navigation Planning in Unstructured Outdoor Environment with Deep Reinforcement Learning
CoverNav: Cover Following Navigation Planning in Unstructured Outdoor Environment with Deep Reinforcement Learning Open
Autonomous navigation in offroad environments has been extensively studied in the robotics field. However, navigation in covert situations where an autonomous vehicle needs to remain hidden from outside observers remains an underexplored a…
View article: Strategic maneuver and disruption with reinforcement learning approaches for multi-agent coordination
Strategic maneuver and disruption with reinforcement learning approaches for multi-agent coordination Open
Reinforcement learning (RL) approaches can illuminate emergent behaviors that facilitate coordination across teams of agents as part of a multi-agent system (MAS), which can provide windows of opportunity in various military tasks. Technol…
View article: Emergent behaviors in multi-agent target acquisition
Emergent behaviors in multi-agent target acquisition Open
Only limited studies and superficial evaluations are available on agents'\nbehaviors and roles within a Multi-Agent System (MAS). We simulate a MAS using\nReinforcement Learning (RL) in a pursuit-evasion (a.k.a predator-prey pursuit)\ngame…
View article: Learning to Guide Multiple Heterogeneous Actors from a Single Human Demonstration via Automatic Curriculum Learning in StarCraft II
Learning to Guide Multiple Heterogeneous Actors from a Single Human Demonstration via Automatic Curriculum Learning in StarCraft II Open
Traditionally, learning from human demonstrations via direct behavior cloning can lead to high-performance policies given that the algorithm has access to large amounts of high-quality data covering the most likely scenarios to be encounte…
View article: On games and simulators as a platform for development of artificial intelligence for command and control
On games and simulators as a platform for development of artificial intelligence for command and control Open
Games and simulators can be a valuable platform to execute complex multi-agent, multiplayer, imperfect information scenarios with significant parallels to military applications: multiple participants manage resources and make decisions tha…
View article: Inferring and Learning Multi-Robot Policies by Observing an Expert
Inferring and Learning Multi-Robot Policies by Observing an Expert Open
We present a technique for learning how to solve a multi-robot mission that requires interaction with an external environment by observing an expert system executing the same mission. We define the expert system as a team of robots equippe…
View article: On Memory Mechanism in Multi-Agent Reinforcement Learning
On Memory Mechanism in Multi-Agent Reinforcement Learning Open
Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems in…
View article: Opinion Formation Threshold Estimates from Different Combinations of Social Media Data-Types
Opinion Formation Threshold Estimates from Different Combinations of Social Media Data-Types Open
Passive consumption of a quantifiable amount of social media information related to a topic can cause individuals to form opinions. If a substantial amount of these individuals are motivated to take action from their recently established o…
View article: Adapting the Predator-Prey Game Theoretic Environment to Army Tactical Edge Scenarios with Computational Multiagent Systems
Adapting the Predator-Prey Game Theoretic Environment to Army Tactical Edge Scenarios with Computational Multiagent Systems Open
The historical origins of the game theoretic predator-prey pursuit problem can be traced back to Benda, et al., 1985 [1]. Their work adapted the predator-prey ecology problem into a pursuit environment focused on the dynamics of cooperativ…
View article: Coordination-driven learning in multi-agent problem spaces
Coordination-driven learning in multi-agent problem spaces Open
We discuss the role of coordination as a direct learning objective in multi-agent reinforcement learning (MARL) domains. To this end, we present a novel means of quantifying coordination in multi-agent systems, and discuss the implications…
View article: Measuring collaborative emergent behavior in multi-agent reinforcement\n learning
Measuring collaborative emergent behavior in multi-agent reinforcement\n learning Open
Multi-agent reinforcement learning (RL) has important implications for the\nfuture of human-agent teaming. We show that improved performance with\nmulti-agent RL is not a guarantee of the collaborative behavior thought to be\nimportant for…
View article: Adapting the Predator-Prey Game Theoretic Environment to Army Tactical\n Edge Scenarios with Computational Multiagent Systems
Adapting the Predator-Prey Game Theoretic Environment to Army Tactical\n Edge Scenarios with Computational Multiagent Systems Open
The historical origins of the game theoretic predator-prey pursuit problem\ncan be traced back to Benda, et al., 1985 [1]. Their work adapted the\npredator-prey ecology problem into a pursuit environment which focused on the\ndynamics of c…
View article: Using the Value of Information (VoI) Metric to Improve Sensemaking
Using the Value of Information (VoI) Metric to Improve Sensemaking Open
Sensemaking is the cognitive process of extracting information, creating schemata from knowledge, making decisions from those schemata, and inferring conclusions. Human analysts are essential to exploring and quantifying this process, but …
View article: The Investigation of Social Media Data Thresholds for Opinion Formation
The Investigation of Social Media Data Thresholds for Opinion Formation Open
The pervasive use of social media has grown to over two billion users to date, and is commonly utilized as a means to share information and shape world events. Evidence suggests that passive social media usage (i.e., viewing without taking…
View article: The Importance of Lateral Connections in the Parietal Cortex for Generating Motor Plans
The Importance of Lateral Connections in the Parietal Cortex for Generating Motor Plans Open
Substantial evidence has highlighted the significant role of associative brain areas, such as the posterior parietal cortex (PPC) in transforming multimodal sensory information into motor plans. However, little is known about how different…