Generating behaviorally diverse policies with latent diffusion models
Abstract Recent progress in Quality Diversity Reinforcement Learning (QD-RL) has enabled
learning a collection of behaviorally diverse, high performing policies. However, these …
learning a collection of behaviorally diverse, high performing policies. However, these …
Density descent for diversity optimization
Diversity optimization seeks to discover a set of solutions that elicit diverse features. Prior
work has proposed Novelty Search (NS), which, given a current set of solutions, seeks to …
work has proposed Novelty Search (NS), which, given a current set of solutions, seeks to …
Bayesian Optimisation for Quality Diversity Search with coupled descriptor functions
Quality Diversity (QD) algorithms such as MAP-Elites are a class of optimisation techniques
that attempt to find many high performing points that all behave differently according to a …
that attempt to find many high performing points that all behave differently according to a …
Hyperppo: A scalable method for finding small policies for robotic control
Models with fewer parameters are necessary for the neural control of memory-limited,
performant robots. Finding these smaller neural network architectures can be time …
performant robots. Finding these smaller neural network architectures can be time …
Adaptive generative adversarial maximum entropy inverse reinforcement learning
L Song, D Li, X Xu - Information Sciences, 2025 - Elsevier
Maximum entropy inverse reinforcement learning algorithms have been extensively studied
for learning rewards and optimizing policies using expert demonstrations. However, high …
for learning rewards and optimizing policies using expert demonstrations. However, high …
Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration
Learning diverse and high-performance behaviors from a limited set of demonstrations is a
grand challenge. Traditional imitation learning methods usually fail in this task because most …
grand challenge. Traditional imitation learning methods usually fail in this task because most …
Quality Diversity Imitation Learning
Imitation learning (IL) has shown great potential in various applications, such as robot
control. However, traditional IL methods are usually designed to learn only one specific type …
control. However, traditional IL methods are usually designed to learn only one specific type …
Scaling Policy Gradient Quality-Diversity with Massive Parallelization via Behavioral Variations
Quality-Diversity optimization comprises a family of evolutionary algorithms aimed at
generating a collection of diverse and high-performing solutions. MAP-Elites (ME), a notable …
generating a collection of diverse and high-performing solutions. MAP-Elites (ME), a notable …
Skill-Conditioned Policy Optimization with Successor Features Representations
A key aspect of intelligence is the ability to exhibit a wide range of behaviors to adapt to
unforeseen situations. Designing artificial agents that are capable of showcasing a broad …
unforeseen situations. Designing artificial agents that are capable of showcasing a broad …
Quality Diversity for Robot Learning: Limitations and Future Directions
Quality Diversity (QD) has shown great success in discovering high-performing, diverse
policies for robot skill learning. While current benchmarks have led to the development of …
policies for robot skill learning. While current benchmarks have led to the development of …