Search Results for author:
Found 10 papers, 2 papers with code
Open-ended search for environments and adapted agents using MAP-Elites
We want to move one step closer to creating simulated environments similar to the diverse real world, where agents can both find solvable tasks, and adapt to them.
Co-optimising Robot Morphology and Controller in a Simulated Open-Ended Environment
We compare the diversity, fitness and robustness of agents evolving in environments generated by POET to agents evolved in handcrafted curricula of environments.
A Model of WiFi Performance With Bounded Latency
Instead of computing throughput numbers from a steady-state analysis of a Markov chain, we explicitly model latency and packet loss.
Networking and Internet Architecture Performance C.2.2; C.2.5; C.4
Quality and Diversity in Evolutionary Modular Robotics
In this paper we compare a single objective Evolutionary Algorithm with two diversity promoting search algorithms; a Multi-Objective Evolutionary Algorithm and MAP-Elites a Quality Diversity algorithm, for the difficult problem of evolving control and morphology in modular robotics.
Self-Adapting Goals Allow Transfer of Predictive Models to New Tasks
In this paper, we extend a recent deep learning architecture which learns a predictive model of the environment that aims to predict only the value of a few key measurements, which are be indicative of an agent's performance.
Model-based Reinforcement Learning
reinforcement-learning
+1
Guiding Neuroevolution with Structural Objectives
However, on a problem where the optimal decomposition is less obvious, the structural diversity objective is found to outcompete other structural objectives -- and this technique can even increase performance on problems without any decomposable structure at all.
How do Mixture Density RNNs Predict the Future?
Gaining a better understanding of how and what machine learning systems learn is important to increase confidence in their decisions and catalyze further research.
Multiobjective Coverage Path Planning: Enabling Automated Inspection of Complex, Real-World Structures
We here test our method on a set of inspection targets with large variation in size and complexity, and compare its performance with two state-of-the-art methods for complete coverage path planning.
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them.
Deep Predictive Models in Interactive Music
Musical performance requires prediction to operate instruments, to perform in groups and to improvise.
