Share This Author
A Survey on Policy Search for Robotics
This work classifies model-free methods based on their policy evaluation strategy, policy update strategy, and exploration strategy and presents a unified view on existing algorithms.
Probabilistic Movement Primitives
This work analytically derive a stochastic feedback controller which reproduces the given trajectory distribution for robot movement control and presents a probabilistic formulation of the MP concept that maintains a distribution over trajectories.
Policy evaluation with temporal differences: a survey and comparison
Policy Evaluation with Temporal Differences: A Survey and Comparison and Comparison Journal of Machine Learning Research, 15, 809-883.
An Algorithmic Perspective on Imitation Learning
- Takayuki Osa, J. Pajarinen, G. Neumann, J. Bagnell, P. Abbeel, Jan Peters
- Computer ScienceFound. Trends Robotics
- 27 March 2018
This work provides an introduction to imitation learning, dividing imitation learning into directly replicating desired behavior and learning the hidden objectives of the desired behavior from demonstrations (called inverse optimal control or inverse reinforcement learning [Russell, 1998]).
Hierarchical Relative Entropy Policy Search
This work defines the problem of learning sub-policies in continuous state action spaces as finding a hierarchical policy that is composed of a high-level gating policy to select the low-level sub-Policies for execution by the agent and treats them as latent variables which allows for distribution of the update information between the sub- policies.
Interaction primitives for human-robot cooperation tasks
- H. B. Amor, G. Neumann, Sanket Kamthe, Oliver Kroemer, Jan Peters
- Computer ScienceIEEE International Conference on Robotics and…
- 7 June 2014
This paper proposes to learn interaction skills by observing how two humans engage in a similar task, and introduces a new representation called Interaction Primitives, which builds on the framework of dynamic motor primitives by maintaining a distribution over the parameters of the DMP.
Using probabilistic movement primitives in robotics
A stochastic feedback controller is derived that reproduces the encoded variability of the movement and the coupling of the degrees of freedom of the robot by using a probabilistic representation.
Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces
- P. Becker, Harit Pandya, Gregor H. W. Gebhardt, Cheng Zhao, C. Taylor, G. Neumann
- Computer ScienceICML
- 17 May 2019
This work proposes a new deep approach to Kalman filtering which can be learned directly in an end-to-end manner using backpropagation without additional approximations and uses a high-dimensional factorized latent state representation for which the Kalman updates simplify to scalar operations and thus avoids hard to backpropagate, computationally heavy and potentially unstable matrix inversions.
Data-Efficient Generalization of Robot Skills with Contextual Policy Search
This work proposes a new model-based policy search approach that can also learn contextual upper-level policies and achieves a substantial improvement in learning speed compared to existing methods on simulated and real robotic tasks.
Variational Inference for Policy Search in changing situations
- G. Neumann
- Computer ScienceICML
- 28 June 2011
Variational Inference for Policy Search (VIP) has several interesting properties and meets the performance of state-of-the-art methods while being applicable to simultaneously learning in multiple situations.