Agents


A16Z AI Playbook

#artificialintelligence

Precisely defining artificial intelligence is tricky. John McCarthy proposed that AI is the simulation of human intelligence by machines for the inaugural summer research project in 1956. Others have defined AI as the study of intelligent agents, human or not, that can perceive their environments and take actions to maximize their chances of achieving some goal. Jerry Kaplan wrestles with the question for an entire chapter in his book Artificial Intelligence: What Everyone Needs To Know before giving up on a succinct definition. Rather than try to define AI precisely, we'll simply differentiate AI's goals and techniques: Some people use Artificial Intelligence and Machine Learning interchangeably.


Publications

#artificialintelligence

Inceoglu I, Thomas G, Chu C, Plans D, Gerbasi A (2018). Leadership behavior and employee well-being: an integrated review and a future research agenda. Lopez D, Brown AW, Plans D. (2019). Modelling and simulation of operation and maintenance strategy for offshore wind farms based on multiagent system. Murphy J, Brewer R, Coll M-P, Plans D, Hall M, Shiu SS, Catmur C, Bird G. (2019).


Researchers Improve Robotic Arm Used in Surgery

#artificialintelligence

Facebook has recently created an algorithm that enhances an AI agent's ability to navigate an environment, letting the agent determine the shortest route through new environments without access to a map. While mobile robots typically have a map programmed into them, the new algorithm that Facebook designed could enable the creation of robots that can navigate environments without the need for maps. According to a post created by Facebook researchers, a major challenge for robot navigation is endowing AI systems with the ability to navigate through novel environments and reaching programmed destinations without a map. In order to tackle this challenge, Facebook created a reinforcement learning algorithm distributed across multiple learners. The algorithm was called decentralized distributed proximal policy optimization (DD-PPO).


AI At The Edge: Creating Coordinated Autonomy

#artificialintelligence

Today organizations have to deal with so many emergent behaviors that the notion of central control as the only coping mechanism seems to be receding as a dominant management model. Freedom must be doled out further from the centrist idea by creating goals, constraints, boundaries and allowable edge behaviors. Someday software and hardware agents will negotiate their contribution to business outcomes on their own, but until then organizations will have to prepare themselves by managing coordinated autonomy. Edge computing is a form of distributed computing which brings computation and data storage closer to the location where it is needed, to improve response times and provide better actions. Now, AI on Edge, can offer a whole lot of new possibilities.



Computing Robust Counter-Strategies

Neural Information Processing Systems

Adaptation to other initially unknown agents often requires computing an effective counter-strategy. In the Bayesian paradigm, one must find a good counter-strategy to the inferred posterior of the other agents' behavior. In the experts paradigm, one may want to choose experts that are good counter-strategies to the other agents' expected behavior. In this paper we introduce a technique for computing robust counter-strategies for adaptation in multiagent scenarios under a variety of paradigms. The strategies can take advantage of a suspected tendency in the decisions of the other agents, while bounding the worst-case performance when the tendency is not observed.


Multi-Agent Filtering with Infinitely Nested Beliefs

Neural Information Processing Systems

In partially observable worlds with many agents, nested beliefs are formed when agents simultaneously reason about the unknown state of the world and the beliefs of the other agents. The multi-agent filtering problem is to efficiently represent and update these beliefs through time as the agents act in the world. In this paper, we formally define an infinite sequence of nested beliefs about the state of the world at the current time $t$ and present a filtering algorithm that maintains a finite representation which can be used to generate these beliefs. In some cases, this representation can be updated exactly in constant time; we also present a simple approximation scheme to compact beliefs if they become too complex. In experiments, we demonstrate efficient filtering in a range of multi-agent domains.


Help or Hinder: Bayesian Models of Social Goal Inference

Neural Information Processing Systems

Everyday social interactions are heavily influenced by our snap judgments about others goals. Even young infants can infer the goals of intentional agents from observing how they interact with objects and other agents in their environment: e.g., that one agent is helping or hindering anothers attempt to get up a hill or open a box. We propose a model for how people can infer these social goals from actions, based on inverse planning in multiagent Markov decision problems (MDPs). The model infers the goal most likely to be driving an agents behavior by assuming the agent acts approximately rationally given environmental constraints and its model of other agents present. Papers published at the Neural Information Processing Systems Conference.


A rational decision making framework for inhibitory control

Neural Information Processing Systems

Intelligent agents are often faced with the need to choose actions with uncertain consequences, and to modify those actions according to ongoing sensory processing and changing task demands. The requisite ability to dynamically modify or cancel planned actions is known as inhibitory control in psychology. We formalize inhibitory control as a rational decision-making problem, and apply to it to the classical stop-signal task. Using Bayesian inference and stochastic control tools, we show that the optimal policy systematically depends on various parameters of the problem, such as the relative costs of different action choices, the noise level of sensory inputs, and the dynamics of changing environmental demands. Our normative model accounts for a range of behavioral data in humans and animals in the stop-signal task, suggesting that the brain implements statistically optimal, dynamically adaptive, and reward-sensitive decision-making in the context of inhibitory control problems.


SpikeAnts, a spiking neuron network modelling the emergence of organization in a complex system

Neural Information Processing Systems

Many complex systems, ranging from neural cell assemblies to insect societies, involve and rely on some division of labor. How to enforce such a division in a decentralized and distributed way, is tackled in this paper, using a spiking neuron network architecture. Specifically, a spatio-temporal model called SpikeAnts is shown to enforce the emergence of synchronized activities in an ant colony. Each ant is modelled from two spiking neurons; the ant colony is a sparsely connected spiking neuron network. Each ant makes its decision (among foraging, sleeping and self-grooming) from the competition between its two neurons, after the signals received from its neighbor ants.