Search Results for author:
Found 23 papers, 3 papers with code
Empowerment -- an Introduction
This book chapter is an introduction to and an overview of the information-theoretic, task independent utility function "Empowerment", which is defined as the channel capacity between an agent's actions and an agent's sensors.
Changing the Environment based on Intrinsic Motivation
One of the remarkable feats of intelligent life is that it restructures the world it lives in for its own benefit.
Changing the Environment Based on Empowerment as Intrinsic Motivation
In this paper we investigate how the information-theoretic measure of agent empowerment can provide a task-independent, intrinsic motivation to restructure the world.
Accelerating Empowerment Computation with UCT Tree Search
Models of intrinsic motivation present an important means to produce sensible behaviour in the absence of extrinsic rewards.
Generative Design in Minecraft (GDMC), Settlement Generation Competition
This paper introduces the settlement generation competition for Minecraft, the first part of the Generative Design in Minecraft challenge.
New And Surprising Ways to Be Mean. Adversarial NPCs with Coupled Empowerment Minimisation
Creating Non-Player Characters (NPCs) that can react robustly to unforeseen player behaviour or novel game content is difficult and time-consuming.
Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop
Research on intrinsic motivations may profit from an additional way to implement intrinsically motivated agents that also share the biological plausibility of active inference.
A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking
This paper introduces an information-theoretic method for selecting a subset of problems which gives the most information about a group of problem-solving algorithms.
Leveling the Playing Field -- Fairness in AI Versus Human Game Benchmarks
The extent to which these games benchmark consist of fair competition between human and AI is also a matter of debate.
Generative Design in Minecraft: Chronicle Challenge
We introduce the Chronicle Challenge as an optional addition to the Settlement Generation Challenge in Minecraft.
Automatic Generation of Level Maps with the Do What's Possible Representation
Automatic generation of level maps is a popular form of automatic content generation.
The Riddle of Togelby
At the 2017 Artificial and Computational Intelligence in Games meeting at Dagstuhl, Julian Togelius asked how to make spaces where every way of filling in the details yielded a good game.
Measuring Time with Minimal Clocks
Clock cascades show a "condensation effect" and the composite clock shows various regimes of markedly different dynamics.
Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Games
Deep reinforcement learning has learned to play many games well, but failed on others.
Human Perception of Intrinsically Motivated Autonomy in Human-Robot Interaction
A challenge in using robots in human-inhabited environments is to design behavior that is engaging, yet robust to the perturbations induced by human interaction.
Warmth and Competence to Predict Human Preference of Robot Behavior in Physical Human-Robot Interaction
We found that Warmth and Competence, among all RoSAS and Godspeed dimensions, are the most important predictors for human preferences between different robot behaviors.
Applications of Artificial Intelligence in Live Action Role-Playing Games (LARP)
Live Action Role-Playing (LARP) games and similar experiences are becoming a popular game genre.
The AI Settlement Generation Challenge in Minecraft: First Year Report
This article outlines what we learned from the first year of the AI Settlement Generation Competition in Minecraft, a competition about producing AI programs that can generate interesting settlements in Minecraft for an unseen map.
Comparing PCG metrics with Human Evaluation in Minecraft Settlement Generation
There are a range of metrics that can be applied to the artifacts produced by procedural content generation, and several of them come with qualitative claims.
Skilled motor control implies a low entropy of states but a high entropy of actions
The mastery of skills such as playing tennis or balancing an inverted pendulum implies a very accurate control of movements to achieve the task goals.
Reliably Re-Acting to Partner's Actions with the Social Intrinsic Motivation of Transfer Empowerment
We consider multi-agent reinforcement learning (MARL) for cooperative communication and coordination tasks.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Automated Isovist Computation for Minecraft
Procedural content generation for games is a growing trend in both research and industry, even though there is no consensus of how good content looks, nor how to automatically evaluate it.
Exploring Minecraft Settlement Generators with Generative Shift Analysis
With growing interest in Procedural Content Generation (PCG) it becomes increasingly important to develop methods and tools for evaluating and comparing alternative systems.
