Search Results for author:
Found 11 papers, 1 papers with code
Interactive incremental learning of generalizable skills with local trajectory modulation
The problem of generalization in learning from demonstration (LfD) has received considerable attention over the years, particularly within the context of movement primitives, where a number of approaches have emerged.
Learning to Exploit Elastic Actuators for Quadruped Locomotion
Spring-based actuators in legged locomotion provide energy-efficiency and improved performance, but increase the difficulty of controller design.
Smooth Exploration for Robotic Reinforcement Learning
We evaluate gSDE both in simulation, on PyBullet continuous control tasks, and directly on three different real robots: a tendon-driven elastic robot, a quadruped and an RC car.
Ranked #1 on
Continuous Control
on PyBullet HalfCheetah
Comparing Semi-Parametric Model Learning Algorithms for Dynamic Model Estimation in Robotics
Physical modeling of robotic system behavior is the foundation for controlling many robotic mechanisms to a satisfactory degree.
Investigating Generalisation in Continuous Deep Reinforcement Learning
Deep Reinforcement Learning has shown great success in a variety of control tasks.
A survey on policy search algorithms for learning robot controllers in a handful of trials
Most policy search algorithms require thousands of training episodes to find an effective policy, which is often infeasible with a physical robot.
Policy Search in Continuous Action Domains: an Overview
Continuous action policy search is currently the focus of intensive research, driven both by the recent success of deep reinforcement learning algorithms and the emergence of competitors based on evolutionary algorithms.
Proximodistal Exploration in Motor Learning as an Emergent Property of Optimization
Here, we formulate and study computationally the hypothesis that such patterns can emerge spontaneously as the result of a family of stochastic optimization processes (evolution strategies with covariance-matrix adaptation), without an innate encoding of a maturational schedule.
Gated networks: an inventory
Gated networks are networks that contain gating connections, in which the outputs of at least two neurons are multiplied.
Learning and Reasoning with Action-Related Places for Robust Mobile Manipulation
We propose the concept of Action-Related Place (ARPlace) as a powerful and flexible representation of task-related place in the context of mobile manipulation.
Path Integral Policy Improvement with Covariance Matrix Adaptation
There has been a recent focus in reinforcement learning on addressing continuous state and action problems by optimizing parameterized policies.
