Corpus ID: 60875658

Reinforcement learning for robots using neural networks

@inproceedings{Lin1992ReinforcementLF,
  title={Reinforcement learning for robots using neural networks},
  author={Longxin Lin},
  year={1992}
}
Reinforcement learning agents are adaptive, reactive, and self-supervised. [...] Key Method Techniques for reducing learning time must be devised. Second, most existing reinforcement learning methods assume that the world is a Markov decision process. This assumption is too strong for many robot tasks of interest. This dissertation demonstrates how we can possibly overcome the slow learning problem and tackle non-Markovian environments, making reinforcement learning more practical for realistic robot tasks: (1…Expand
Scaling Up Reinforcement Learning for Robot Control
TLDR
This research concludes that it is possible to build artificial agents that can acquire complex control policies effectively by reinforcement learning and enable its applications to complex robot- learning problems. Expand
Safer reinforcement learning for robotics
Reinforcement learning is an active research area in the fields of artificial intelligence and machine learning, with applications in control. The most important feature of reinforcement learning isExpand
TEXPLORE: real-time sample-efficient reinforcement learning for robots
The use of robots in society could be expanded by using reinforcement learning (RL) to allow robots to learn and adapt to new situations online. RL is a paradigm for learning sequential decisionExpand
Q-learning for Robots
TLDR
Q-learning is sought using reinforcement learning techniques – in particular Q-learning which does not require a model of the robot-world interaction, where the Q value is the utility of executing the action in the situation. Expand
Towards a common implementation of reinforcement learning for multiple robotic tasks
TLDR
A practical core implementation of RL is presented, which enables the learning process for multiple robotic tasks with minimal per-task tuning or none, and a novel approach for action selection, called Q-biased softmax regression (QBIASSR), that takes advantage of the structure of the state space by attending the physical variables involved. Expand
Guided Deep Reinforcement Learning for Swarm Systems
TLDR
This paper investigates how to learn to control a group of cooperative agents with limited sensing capabilities such as robot swarms, where the actors base their decisions only on locally sensed information and the critic is learned based on the true global state. Expand
Q-learning for Robots 1 Q-learning for Robots
Robot learning is a challenging – and somewhat unique – research domain. If a robot behavior is defined as a mapping between situations that occurred in the real world and actions to be accomplished,Expand
Guided Deep Reinforcement Learning for Robot Swarms Guided Deep Reinforcement Learning
In this thesis, we provide the framework of multi-agent guided deterministic policy gradient for reinforcement learning in cooperative multi-agent systems. The multi-agent scenario is formulated as aExpand
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
TEXPLORE: Temporal Difference Reinforcement Learning for Robots and Time-Constrained Domains
  • Todd Hester
  • Computer Science
  • Studies in Computational Intelligence
  • 2013
TLDR
This book presents and develops new reinforcement learning methods that enable fast and robust learning on robots in real-time and focuses on time-constrained domains where the first challenge is critically important. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 78 REFERENCES
Input Generalization in Delayed Reinforcement Learning: An Algorithm and Performance Comparisons
TLDR
This paper describes the input generalization problem (whereby the system must generalize to produce similar actions in similar situations) and an implemented solution, the G algorithm, which is based on recursive splitting of the state space based on statistical measures of differences in reinforcements received. Expand
Learning in embedded systems
TLDR
This dissertation addresses the problem of designing algorithms for learning in embedded systems using Sutton's techniques for linear association and reinforcement comparison, while the interval estimation algorithm uses the statistical notion of confidence intervals to guide its generation of actions. Expand
Programming Robots Using Reinforcement Learning and Teaching
TLDR
This paper presents a general approach to making robots which can improve their performance from experiences as well as from being taught, and develops a simulated learning robot which could learn three moderately complex behaviors and use what was learned in the simulator to operate in the real world quite successfully. Expand
Memory Approaches to Reinforcement Learning in Non-Markovian Domains
TLDR
This paper studies three connectionist approaches which learn to use history to handle perceptual aliasing: the window-Q, recurrent- Q, and recurrent-model architectures. Expand
Explanation-Based Neural Network Learning for Robot Control
TLDR
A neural network learning method that generalizes rationally from many fewer data points, relying instead on prior knowledge encoded in previously learned neural networks that is used to bias generalization when learning the target function. Expand
Efficient memory-based learning for robot control
TLDR
A method of learning is presented in which all the experiences in the lifetime of the robot are explicitly remembered, thus permitting very quick predictions of the e ects of proposed actions and, given a goal behaviour, permitting fast generation of a candidate action. Expand
Self-improving reactive agents: case studies of reinforcement learning frameworks
TLDR
This paper describes the learning agents and their performance, and summarizes the learning algorithms and the lessons I learned from this study. Expand
Reinforcement Learning with a Hierarchy of Abstract Models
TLDR
Simulations on a set of compositionally-structured navigation tasks show that H-DYNA can learn to solve them faster than conventional RL algorithms, and the abstract models can be used to solve stochastic control tasks. Expand
Learning a Cost-Sensitive Internal Representation for Reinforcement Learning
TLDR
The approach learns a task-dependent internal representation and a decision policy simultaneously in a finite, deterministic environment and maximizes the long-term discounted reward per action and reduces the average sensing cost per state. Expand
Scaling Reinforcement Learning to Robotics by Exploiting the Subsumption Architecture
TLDR
This paper shows how problems are overcome by using a subsumption architecture: each module can be given its own simple reward function, and state history information can be easily encoded in a module's applicability predicate. Expand
...
1
2
3
4
5
...