Search Results for author:
Found 17 papers, 7 papers with code
A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents
A lot of recent machine learning research papers have ``open-ended learning'' in their title.
Integrating LLMs and Decision Transformers for Language Grounded Generative Quality-Diversity
Quality-Diversity is a branch of stochastic optimization that is often applied to problems from the Reinforcement Learning and control domains in order to construct repertoires of well-performing policies/skills that exhibit diversity with respect to a behavior space.
Data-efficient, Explainable and Safe Box Manipulation: Illustrating the Advantages of Physical Priors in Model-Predictive Control
Model-based RL/control have gained significant traction in robotics.
E2R: a Hierarchical-Learning inspired Novelty-Search method to generate diverse repertoires of grasping trajectories
Robotics grasping refers to the task of making a robotic system pick an object by applying forces and torques on its surface.
Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equations
Model-based Reinforcement Learning and Control have demonstrated great potential in various sequential decision making problem domains, including in robotics settings.
Geodesics, Non-linearities and the Archive of Novelty Search
An argument that is often encountered in the literature is that the archive prevents exploration from backtracking or cycling, i. e. from revisiting previously encountered areas in the behavior space.
Towards QD-suite: developing a set of benchmarks for Quality-Diversity algorithms
Inspired by recent works on Reinforcement Learning benchmarks, we argue that the identification of challenges faced by QD methods and the development of targeted, challenging, scalable but affordable benchmarks is an important step.
Discovering and Exploiting Sparse Rewards in a Learned Behavior Space
Learning optimal policies in sparse rewards settings is difficult as the learning agent has little to no feedback on the quality of its actions.
Few-shot Quality-Diversity Optimization
Experiments carried in both sparse and dense reward settings using robotic manipulation and navigation benchmarks show that it considerably reduces the number of generations that are required for QD optimization in these environments.
BR-NS: an Archive-less Approach to Novelty Search
In this paper, we discuss an alternative approach to novelty estimation, dubbed Behavior Recognition based Novelty Search (BR-NS), which does not require an archive, makes no assumption on the metrics that can be defined in the behavior space and does not rely on nearest neighbours search.
Sparse Reward Exploration via Novelty Search and Emitters
Contrary to existing emitters-based approaches, SERENE separates the search space exploration and reward exploitation into two alternating processes.
DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics
Robots are still limited to controlled conditions, that the robot designer knows with enough details to endow the robot with the appropriate models or behaviors.
Novelty Search makes Evolvability Inevitable
Evolvability is thus a natural byproduct of the search in this context.
Unsupervised Learning and Exploration of Reachable Outcome Space
Results show that TAXONS can find a diverse set of controllers, covering a good part of the ground-truth outcome space, while having no information about such space.
Building an Affordances Map with Interactive Perception
Robots need to understand their environment to perform their task.
From exploration to control: learning object manipulation skills through novelty search and local adaptation
The approach has been validated on two different experiments on the Baxter robot: a ball launching and a joystick manipulation tasks.
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.
