• Corpus ID: 5776535

Training and Tracking in Robotics

@inproceedings{Selfridge1985TrainingAT,
  title={Training and Tracking in Robotics},
  author={Oliver G. Selfridge and Richard S. Sutton and Andrew G. Barto},
  booktitle={IJCAI},
  year={1985}
}
We explore the use of learning schemes in training and adapting performance on simple coordination tasks. The tasks are 1-D pole balancing. Several programs incorporating learning have already achieved this (1, S, 8): the problem is to move a cart along a short piece of track to at to keep a pole balanced on its end; the pole is hinged to the cart at its bottom, and the cart is moved either to the left or to the right by a force of constant magnitude. The form of the task considered here, after… 
A Neural Network Pole Balancer that Learns and Operates on a Real Robot in Real Time
TLDR
A neural network approach to the classic inverted pendulum task is presented and is demonstrated to be effective for the real-time control of a small, selfcontained mini-robot, specially outfitted for the task.
Learning arm kinematics and dynamics.
  • C. Atkeson
  • Psychology
    Annual review of neuroscience
  • 1989
In this review I have discussed how the form of representation used in internal models of the motor apparatus affects how and what a system can learn. Tabular models and structured models have
Reinforcement Learning from Demonstration
TLDR
It is shown that human demonstrators with varying skills can help RL agents to learn tasks more efficiently, and that when prior knowledge is available RL agents can learn a task faster.
Reinforcement Learning with Converging Goal Space and Binary Reward Function
TLDR
This paper presents a simple method called Converging Goal Space and Binary Reward Function, which helps agents learn tasks easily and efficiently in large environments while providing a binary reward.
Tensor Based Knowledge Transfer Across Skill Categories for Robot Control
TLDR
A class of neural network controllers that can realise four distinct skill classes: reaching, object throwing, casting, and ball-in-cup are introduced and factorising the weights of the neural network is able to extract transferrable latent skills that enable dramatic acceleration of learning in cross-task transfer.
Learning to Control with Automatic
TLDR
It is demonstrated that the new method, called STAQ (Set Training with Automatic Quantization), can aggressively partition the input variables to a finer resolution until the correct control rules based on these partitions (symbols) are learned.
Automatic Curriculum Learning For Deep RL: A Short Survey
TLDR
The ambition of this work is to present a compact and accessible introduction to the Automatic Curriculum Learning literature and to draw a bigger picture of the current state of the art in ACL to encourage the cross-breeding of existing concepts and the emergence of new ideas.
Reinforcement learning and its application to control
TLDR
It is argued that for certain types of problems the latter approach, of which reinforcement learning is an example, can yield faster, more reliable learning, while the former approach is relatively inefficient.
...
...

References

SHOWING 1-10 OF 13 REFERENCES
Neuronlike adaptive elements that can solve difficult learning control problems
TLDR
It is shown how a system consisting of two neuronlike adaptive elements can solve a difficult learning control problem and the relation of this work to classical and instrumental conditioning in animal learning studies and its possible implications for research in the neurosciences.
Some Studies in Machine Learning Using the Game of Checkers
  • A. Samuel
  • Computer Science
    IBM J. Res. Dev.
  • 1959
TLDR
A new signature-table technique is described together with an improved book-learning procedure which is thought to be much superior to the linear polynomial method and to permit the program to look ahead to a much greater depth than it otherwise could do.
Learning Structural Descriptions From Examples
Massachusetts Institute of Technology. Dept. of Electrical Engineering. Thesis. 1970. Ph.D.
Temporal aspects of credit assignment in reinforcement learning
  • Univ. of Massachusetts Technical Report 84-2,
  • 1984
Dynamics of Physical Systems
Learning and Problem Solving
The psychology of computer vision
Learning in random nets Information Theory: Fourth London Symposium
  • Learning in random nets Information Theory: Fourth London Symposium
  • 1961
Pattern-recognising control systems
  • In Tow,
  • 1964
Learning in random nets
  • Information Theory: Fourth London Symposium. London: Butterworths,
  • 1961
...
...