Picture for Manon Flageat

Manon Flageat

AIRL, Imperial College London

Large Language Models as In-context AI Generators for Quality-Diversity

Add code
Apr 24, 2024
Figure 1 for Large Language Models as In-context AI Generators for Quality-Diversity
Figure 2 for Large Language Models as In-context AI Generators for Quality-Diversity
Figure 3 for Large Language Models as In-context AI Generators for Quality-Diversity
Figure 4 for Large Language Models as In-context AI Generators for Quality-Diversity
Viaarxiv icon

Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms

Add code
Dec 12, 2023
Viaarxiv icon

Mix-ME: Quality-Diversity for Multi-Agent Learning

Add code
Nov 03, 2023
Figure 1 for Mix-ME: Quality-Diversity for Multi-Agent Learning
Figure 2 for Mix-ME: Quality-Diversity for Multi-Agent Learning
Figure 3 for Mix-ME: Quality-Diversity for Multi-Agent Learning
Figure 4 for Mix-ME: Quality-Diversity for Multi-Agent Learning
Viaarxiv icon

QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration

Add code
Aug 07, 2023
Figure 1 for QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration
Figure 2 for QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration
Figure 3 for QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration
Figure 4 for QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration
Viaarxiv icon

Benchmark tasks for Quality-Diversity applied to Uncertain domains

Add code
Apr 26, 2023
Figure 1 for Benchmark tasks for Quality-Diversity applied to Uncertain domains
Figure 2 for Benchmark tasks for Quality-Diversity applied to Uncertain domains
Figure 3 for Benchmark tasks for Quality-Diversity applied to Uncertain domains
Figure 4 for Benchmark tasks for Quality-Diversity applied to Uncertain domains
Viaarxiv icon

Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains

Add code
Apr 07, 2023
Figure 1 for Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains
Figure 2 for Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains
Figure 3 for Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains
Figure 4 for Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains
Viaarxiv icon

Multiple Hands Make Light Work: Enhancing Quality and Diversity using MAP-Elites with Multiple Parallel Evolution Strategies

Add code
Mar 10, 2023
Figure 1 for Multiple Hands Make Light Work: Enhancing Quality and Diversity using MAP-Elites with Multiple Parallel Evolution Strategies
Figure 2 for Multiple Hands Make Light Work: Enhancing Quality and Diversity using MAP-Elites with Multiple Parallel Evolution Strategies
Figure 3 for Multiple Hands Make Light Work: Enhancing Quality and Diversity using MAP-Elites with Multiple Parallel Evolution Strategies
Figure 4 for Multiple Hands Make Light Work: Enhancing Quality and Diversity using MAP-Elites with Multiple Parallel Evolution Strategies
Viaarxiv icon

Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning

Add code
Mar 10, 2023
Figure 1 for Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning
Figure 2 for Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning
Figure 3 for Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning
Figure 4 for Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning
Viaarxiv icon

MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation into a Single Policy

Add code
Mar 07, 2023
Figure 1 for MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation into a Single Policy
Figure 2 for MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation into a Single Policy
Figure 3 for MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation into a Single Policy
Figure 4 for MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation into a Single Policy
Viaarxiv icon

Uncertain Quality-Diversity: Evaluation methodology and new methods for Quality-Diversity in Uncertain Domains

Add code
Feb 01, 2023
Figure 1 for Uncertain Quality-Diversity: Evaluation methodology and new methods for Quality-Diversity in Uncertain Domains
Figure 2 for Uncertain Quality-Diversity: Evaluation methodology and new methods for Quality-Diversity in Uncertain Domains
Figure 3 for Uncertain Quality-Diversity: Evaluation methodology and new methods for Quality-Diversity in Uncertain Domains
Figure 4 for Uncertain Quality-Diversity: Evaluation methodology and new methods for Quality-Diversity in Uncertain Domains
Viaarxiv icon