Practical methods of optimization; (2nd ed.)
Practical methods of optimization; (2nd ed.)
Likelihood ratio gradient estimation for stochastic systems
Communications of the ACM - Special issue on simulation
Natural gradient works efficiently in learning
Neural Computation
Likelilood ratio gradient estimation: an overview
WSC '87 Proceedings of the 19th conference on Winter simulation
Statistical machine learning and combinatorial optimization
Theoretical aspects of evolutionary computing
Learning Control Under Extreme Uncertainty
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Reinforcement Learning for Biped Locomotion
ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
PEGASUS: A policy search method for large MDPs and POMDPs
UAI '00 Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence
The Optimal Reward Baseline for Gradient-Based Reinforcement Learning
UAI '01 Proceedings of the 17th Conference in Uncertainty in Artificial Intelligence
Feature Article: Optimization for simulation: Theory vs. Practice
INFORMS Journal on Computing
Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
The Journal of Machine Learning Research
Machine learning of motor skills for robotics
Machine learning of motor skills for robotics
Reinforcement learning for a CPG-driven biped robot
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Learning CPG sensory feedback with policy gradient for biped locomotion for a full-body humanoid
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 3
Experiments with infinite-horizon, policy-gradient estimation
Journal of Artificial Intelligence Research
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Efficient gradient estimation for motor control learning
UAI'03 Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence
An RLS-based natural actor-critic algorithm for locomotion of a two-linked robot arm
CIS'05 Proceedings of the 2005 international conference on Computational Intelligence and Security - Volume Part I
ECML'05 Proceedings of the 16th European conference on Machine Learning
Gaussian process dynamic programming
Neurocomputing
Reinforcement learning for robot soccer
Autonomous Robots
2010 Special Issue: Parameter-exploring policy gradients
Neural Networks
Task-specific generalization of discrete and periodic dynamic movement primitives
IEEE Transactions on Robotics
Learning visual representations for perception-action systems
International Journal of Robotics Research
A Generalized Path Integral Control Approach to Reinforcement Learning
The Journal of Machine Learning Research
ACM Transactions on Speech and Language Processing (TSLP)
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Improving Gaussian process value function approximation in policy gradient algorithms
ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
Preference-based policy learning
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part I
Landau theory of meta-learning
SIIS'11 Proceedings of the 2011 international conference on Security and Intelligent Information Systems
Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives
Robotics and Autonomous Systems
A Novel Trajectory Generation Method for Robot Control
Journal of Intelligent and Robotic Systems
APRIL: active preference learning-based reinforcement learning
ECML PKDD'12 Proceedings of the 2012 European conference on Machine Learning and Knowledge Discovery in Databases - Volume Part II
Active learning of inverse models with intrinsically motivated goal exploration in robots
Robotics and Autonomous Systems
Control of a free-falling cat by policy-based reinforcement learning
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
Dynamical movement primitives: Learning attractor models for motor behaviors
Neural Computation
From dynamic movement primitives to associative skill memories
Robotics and Autonomous Systems
Learning to select and generalize striking movements in robot table tennis
International Journal of Robotics Research
Reinforcement learning in robotics: A survey
International Journal of Robotics Research
Interaction learning for dynamic movement primitives used in cooperative robotic tasks
Robotics and Autonomous Systems
Movement primitives as a robotic tool to interpret trajectories through learning-by-doing
International Journal of Automation and Computing
Fast damage recovery in robotics with the T-resilience algorithm
International Journal of Robotics Research
Socially guided intrinsic motivation for robot learning of motor skills
Autonomous Robots
A tour of machine learning: An AI perspective
AI Communications - ECAI 2012 Turing and Anniversary Track
Hi-index | 0.00 |
Autonomous learning is one of the hallmarks of human and animal behavior, and understanding the principles of learning will be crucial in order to achieve true autonomy in advanced machines like humanoid robots. In this paper, we examine learning of complex motor skills with human-like limbs. While supervised learning can offer useful tools for bootstrapping behavior, e.g., by learning from demonstration, it is only reinforcement learning that offers a general approach to the final trial-and-error improvement that is needed by each individual acquiring a skill. Neither neurobiological nor machine learning studies have, so far, offered compelling results on how reinforcement learning can be scaled to the high-dimensional continuous state and action spaces of humans or humanoids. Here, we combine two recent research developments on learning motor control in order to achieve this scaling. First, we interpret the idea of modular motor control by means of motor primitives as a suitable way to generate parameterized control policies for reinforcement learning. Second, we combine motor primitives with the theory of stochastic policy gradient learning, which currently seems to be the only feasible framework for reinforcement learning for humanoids. We evaluate different policy gradient methods with a focus on their applicability to parameterized motor primitives. We compare these algorithms in the context of motor primitive learning, and show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm.