The Frost Hollow Experiments: Pavlovian Signalling as a Path to Coordination and Communication Between Agents

  title={The Frost Hollow Experiments: Pavlovian Signalling as a Path to Coordination and Communication Between Agents},
  author={Patrick M. Pilarski and Andrew Butcher and Elnaz Davoodi and Michael Bradley Johanson and Dylan J. A. Brenneis and Adam S. R. Parker and Leslie Acker and Matthew M. Botvinick and Joseph Modayil and Adam White},
environment: Observations for the player include the current position, a one-hot vector with one entry per location, hazard presence or absence via a boolean indicating if the wind is currently blowing, and heat, a scalar in [0, heat capacity] indicating how much heat the player has collected. Actions for the player take the form of movement: an integer in [-1, 0, 1], that moves the agent deterministically to an adjacent location (-1, 1) or allows the agent to stay in the same location (0… 

Assessing Human Interaction in Virtual Reality With Continually Learning Prediction Agents Based on Reinforcement Learning Algorithms: A Pilot Study

This research presents a state-of-the-art probabilistic architecture for machine intelligence that combines natural language processing, artificial intelligence, and reinforcement learning into a coherent model.

The Alberta Plan for AI Research

History suggests that the road to a firm research consensus is extraordinarily arduous. Herein we describe our approach to artificial intelligence (AI) research, which we call the Alberta Plan . The



Emergent Multi-Agent Communication in the Deep Learning Era

This article surveys representative recent language emergence studies from a scientific and applied perspective about how language evolves in communities of deep agents and its emergent features are understood.

The Neural Basis of Timing: Distributed Mechanisms for Diverse Functions

Time cells in the hippocampus: a new dimension for mapping memories

The robust representation of both time and space in the hippocampus suggests a fundamental mechanism for organizing the elements of experience into coherent memories.

Reinforcement Learning: An Introduction

This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.

Your brain is a time machine: the neuroscience and physics of time

  • W.W. Norton & Company, New York.
  • 2017

Communicative Capital for Prosthetic Agents

The hypothesis that assistive devices, and specifically artificial arms and hands, can and should be viewed as agents is developed and a new schema for interpreting the capacity of a human-machine collaboration as a function of both the human's and machine's degrees of agency is proposed.

The sense of agency in human-human vs human-robot joint action

Speaking Our Minds: Why human communication is different, and how language evolved to make it special

1. Two Approaches to Communication 2. The Emergence of Communication Systems 3. Cognition and Communication 4. The Evolution of Ostensive Communication 5. Crossing the Rubicon 6. Evolutionary

Integrating time from experience in the lateral entorhinal cortex

It is shown in freely foraging rats that temporal information is robustly encoded across time scales from seconds to hours within the overall population state of the lateral entorhinal cortex, suggesting that populations of lateral entorsal cortex neurons represent time inherently through the encoding of experience.