Algorithms for reinforcement learning
By: Szepesvari, Csaba.
Material type:
BookSeries: Synthesis lectures on artificial intelligence and machine learning #9. Publisher: UK: Morgan & Claypool, 2010Description: xii, 89 p. : ill.; 23.5 cm.ISBN: 9781608454921.Subject(s): Machine learning | Natural gradient | Policy gradient | Actor-critic methods | Q-learning | PAC-learning | Planning | Simulation | Online learning | Active learning | Bias-variance tradeoff | Overfitting | Least-squares methods | Stochastic gradient methods | Function approximation | Simulation optimization | Two-timescale stochastic approximation | Monte-Carlo methods | Stochastic approximation | Mathematical models | Temporal difference learning | Engineering & Applied Sciences | Markov decision processesDDC classification: 006.31 Summary: Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner's predictions. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms'
| Item type | Current location | Call number | Status | Date due | Barcode |
|---|---|---|---|---|---|
| Books | 006.31 SZE (Browse shelf) | Checked out | 15/05/2024 | 031611 |
Includes bibliographical references.
Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner's predictions. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms'
There are no comments for this item.