Search Results for author:
Found 4 papers, 2 papers with code
Parametric-Task MAP-Elites
In this paper, we introduce Parametric-Task MAP-Elites (PT-ME), a new black-box algorithm for continuous multi-task optimization problems.
First do not fall: learning to exploit a wall with a damaged humanoid robot
This article introduces a method, called D-Reflex, that learns a neural network that chooses this contact position given the wall orientation, the wall distance, and the posture of the robot.
Meta-Reinforcement Learning for Adaptive Motor Control in Changing Robot Dynamics and Environments
This work developed a meta-learning approach that adapts the control policy on the fly to different changing conditions for robust locomotion.
Fast Online Adaptation in Robotics through Meta-Learning Embeddings of Simulated Priors
Meta-learning algorithms can accelerate the model-based reinforcement learning (MBRL) algorithms by finding an initial set of parameters for the dynamical model such that the model can be trained to match the actual dynamics of the system with only a few data-points.
