Reinforcement Learning to Adjust Robot Movements to New Situations

@inproceedings{Kober2011ReinforcementLT,
  title={Reinforcement Learning to Adjust Robot Movements to New Situations},
  author={J. Kober and Erhan {\"O}ztop and Jan Peters},
  booktitle={IJCAI},
  year={2011}
}
Many complex robot motor skills can be represented using elementary movements, and there exist efficient techniques for learning parametrized motor plans using demonstrations and self-improvement. However with current techniques, in many cases, the robot currently needs to learn a new elementary movement even if a parametrized motor plan exists that covers a related situation. A method is needed that modulates the elementary movement through the meta-parameters of its representation. In this… Expand
Reinforcement learning to adjust parametrized motor primitives to new situations
TLDR
This paper proposes a method that learns to generalize parametrized motor plans by adapting a small set of global parameters, called meta-parameters, and introduces an appropriate reinforcement learning algorithm based on a kernelized version of the reward-weighted regression. Expand
Learning Motor Skills - From Algorithms to Robot Experiments
TLDR
This book illustrates a method that learns to generalize parameterized motor plans which is obtained by imitation or reinforcement learning, by adapting a small set of global parameters and appropriate kernel-based reinforcement learning algorithms. Expand
Learning motor skills: from algorithms to robot experiments
  • J. Kober
  • Computer Science
  • it Inf. Technol.
  • 2012
TLDR
It is shown how motor primitives can be employed to learn motor skills on three different levels, which contributes to the state of the art in reinforcement learning applied to robotics both in terms of novel algorithms and applications. Expand
Robot Beerpong: Model-Based Learning for Shifting Targets
De ning controls for robot to achieve precise goal-directed movements can be hard when using hand crafted solutions. Reinforcement Learning, particularly policy-search methods provides a promisingExpand
Robot Motor Skill Transfer With Alternate Learning in Two Spaces.
TLDR
This article proposes a framework to represent the policy and conduct imitation learning and optimization for robot intelligent trajectory planning, based on the improved locally weighted regression (iLWR) and policy improvement with path integral by dual perturbation (PI²-DP). Expand
Non-parametric Imitation Learning of Robot Motor Skills
TLDR
A novel kernel treatment of imitation learning is proposed, which endows the robot with imitative and adaptive capabilities and is capable of learning human skills associated with high-dimensional inputs. Expand
Generative Models for Learning Robot Manipulation Skills from Humans
TLDR
This study shows that the proposed manipulation assistance formulations improve the performance of the teleoperator by reducing the task errors and the execution time, while catering for the environmental differences in performing remote manipulation tasks with limited bandwidth and communication delays. Expand
Learning contact-rich manipulation skills with guided policy search
TLDR
This paper extends a recently developed policy search method and uses it to learn a range of dynamic manipulation behaviors with highly general policy representations, without using known models or example demonstrations, and shows that this method can acquire fast, fluent behaviors after only minutes of interaction time. Expand
Towards Robot Task Planning From Probabilistic Models of Human Skills
TLDR
An algorithm for motion planning based on expert demonstrations of a skill to enable execution of complex tasks based on a library of probabilistic skill models that can be combined to accomplish complex tasks in hybrid domains. Expand
Information-Theoretic Motor Skill Learning
TLDR
This paper shows how to adapt the relative entropy policy search (REPS) algorithm for learning parametrized options and extend the algorithm in a mathematical sound way such that it can meet all the requirements for motor skill learning. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 38 REFERENCES
Policy Search for Motor Primitives in Robotics
TLDR
This paper extends previous work on policy learning from the immediate reward case to episodic reinforcement learning, resulting in a general, common framework also connected to policy gradient methods and yielding a novel algorithm for policy learning that is particularly well-suited for dynamic motor primitives. Expand
Learning from demonstration: repetitive movements for autonomous service robotics
This paper presents a method for learning and generating rhythmic movement patterns based on a simple central oscillator. It can be used to generate cyclic movements for a robot system which has toExpand
Policy Gradient Methods for Robotics
  • Jan Peters, S. Schaal
  • Engineering, Computer Science
  • 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2006
TLDR
An overview on learning with policy gradient methods for robotics with a strong focus on recent advances in the field is given and how the most recently developed methods can significantly improve learning performance is shown. Expand
Reinforcement learning by reward-weighted regression for operational space control
TLDR
This work uses a generalization of the EM-base reinforcement learning framework suggested by Dayan & Hinton to reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. Expand
Learning Robot Control - Using Control Policies as Abstract Actions
Autonomous robot systems operating in an uncertain environment have to be able to cope with new situations and task requirements. Important properties of the control architecture of such systems areExpand
Learning table tennis with a Mixture of Motor Primitives
TLDR
This work presents a new approach, called Mixture of Motor Primitives that uses a gating network to activate appropriate motor primitives and shows that the resulting setup was capable of playing rudimentary table tennis using an anthropomorphic robot arm. Expand
Learning nonparametric policies by imitation
TLDR
A new probabilistic approach to the problem of teaching a high degree-of-freedom robot (in particular, a humanoid robot) flexible and generalizable skills via imitation of a human teacher is proposed and produces a nonparametric policy for sensor-based feedback control in continuous state and action spaces. Expand
Learning Attractor Landscapes for Learning Motor Primitives
TLDR
By nonlinearly transforming the canonical attractor dynamics using techniques from nonparametric regression, almost arbitrary new nonlinear policies can be generated without losing the stability properties of the canonical system. Expand
Roles of Macro-Actions in Accelerating Reinforcement Learning
TLDR
Although eligibility traces increased the rate of convergence to the optimal value function compared to learning with macro-actions but without eligibility traces, eligibility traces did not permit the optimal policy to be learned as quickly as it was using macro- actions. Expand
Trajectory prediction: learning to map situations to robot trajectories
TLDR
Experiments on a simulated humanoid reaching problem show that the proposed sparse feature selection approach can predict reasonable motion prototypes in new situations for which the refinement is much faster than an optimization from scratch. Expand
...
1
2
3
4
...