Searching for reinforcement learning : 9 results found | RSS Feed for this search

16.410 Principles of Autonomy and Decision Making (MIT) 16.410 Principles of Autonomy and Decision Making (MIT)

Description

This course surveys a variety of reasoning, optimization, and decision-making methodologies for creating highly autonomous systems and decision support aids. The focus is on principles, algorithms, and their applications, taken from the disciplines of artificial intelligence and operations research. Reasoning paradigms include logic and deduction, heuristic and constraint-based search, model-based reasoning, planning and execution, reasoning under uncertainty, and machine learning. Optimization paradigms include linear, integer and dynamic programming. Decision-making paradigms include decision theoretic planning, and Markov decision processes. This course is offered both to undergraduate (16.410) students as a professional area undergraduate subject, in the field of aerospace information This course surveys a variety of reasoning, optimization, and decision-making methodologies for creating highly autonomous systems and decision support aids. The focus is on principles, algorithms, and their applications, taken from the disciplines of artificial intelligence and operations research. Reasoning paradigms include logic and deduction, heuristic and constraint-based search, model-based reasoning, planning and execution, reasoning under uncertainty, and machine learning. Optimization paradigms include linear, integer and dynamic programming. Decision-making paradigms include decision theoretic planning, and Markov decision processes. This course is offered both to undergraduate (16.410) students as a professional area undergraduate subject, in the field of aerospace information

Subjects

autonomy | autonomy | decision | decision | decision-making | decision-making | reasoning | reasoning | optimization | optimization | autonomous | autonomous | autonomous systems | autonomous systems | decision support | decision support | algorithms | algorithms | artificial intelligence | artificial intelligence | a.i. | a.i. | operations | operations | operations research | operations research | logic | logic | deduction | deduction | heuristic search | heuristic search | constraint-based search | constraint-based search | model-based reasoning | model-based reasoning | planning | planning | execution | execution | uncertainty | uncertainty | machine learning | machine learning | linear programming | linear programming | dynamic programming | dynamic programming | integer programming | integer programming | network optimization | network optimization | decision analysis | decision analysis | decision theoretic planning | decision theoretic planning | Markov decision process | Markov decision process | scheme | scheme | propositional logic | propositional logic | constraints | constraints | Markov processes | Markov processes | computational performance | computational performance | satisfaction | satisfaction | learning algorithms | learning algorithms | system state | system state | state | state | search treees | search treees | plan spaces | plan spaces | model theory | model theory | decision trees | decision trees | function approximators | function approximators | optimization algorithms | optimization algorithms | limitations | limitations | tradeoffs | tradeoffs | search and reasoning | search and reasoning | game tree search | game tree search | local stochastic search | local stochastic search | stochastic | stochastic | genetic algorithms | genetic algorithms | constraint satisfaction | constraint satisfaction | propositional inference | propositional inference | rule-based systems | rule-based systems | rule-based | rule-based | model-based diagnosis | model-based diagnosis | neural nets | neural nets | reinforcement learning | reinforcement learning | web-based | web-based | search trees | search trees

License

Content within individual OCW courses is (c) by the individual authors unless otherwise noted. MIT OpenCourseWare materials are licensed by the Massachusetts Institute of Technology under a Creative Commons License (Attribution-NonCommercial-ShareAlike). For further information see http://ocw.mit.edu/terms/index.htm

Site sourced from

http://ocw.mit.edu/rss/all/mit-allarchivedcourses.xml

Attribution

Click to get HTML | Click to get attribution | Click to get URL

All metadata

See all metadata

16.410 Principles of Autonomy and Decision Making (MIT) 16.410 Principles of Autonomy and Decision Making (MIT)

Description

This course surveys a variety of reasoning, optimization, and decision-making methodologies for creating highly autonomous systems and decision support aids. The focus is on principles, algorithms, and their applications, taken from the disciplines of artificial intelligence and operations research. Reasoning paradigms include logic and deduction, heuristic and constraint-based search, model-based reasoning, planning and execution, reasoning under uncertainty, and machine learning. Optimization paradigms include linear, integer and dynamic programming. Decision-making paradigms include decision theoretic planning, and Markov decision processes. This course is offered both to undergraduate (16.410) students as a professional area undergraduate subject, in the field of aerospace information This course surveys a variety of reasoning, optimization, and decision-making methodologies for creating highly autonomous systems and decision support aids. The focus is on principles, algorithms, and their applications, taken from the disciplines of artificial intelligence and operations research. Reasoning paradigms include logic and deduction, heuristic and constraint-based search, model-based reasoning, planning and execution, reasoning under uncertainty, and machine learning. Optimization paradigms include linear, integer and dynamic programming. Decision-making paradigms include decision theoretic planning, and Markov decision processes. This course is offered both to undergraduate (16.410) students as a professional area undergraduate subject, in the field of aerospace information

Subjects

autonomy | autonomy | decision | decision | decision-making | decision-making | reasoning | reasoning | optimization | optimization | autonomous | autonomous | autonomous systems | autonomous systems | decision support | decision support | algorithms | algorithms | artificial intelligence | artificial intelligence | a.i. | a.i. | operations | operations | operations research | operations research | logic | logic | deduction | deduction | heuristic search | heuristic search | constraint-based search | constraint-based search | model-based reasoning | model-based reasoning | planning | planning | execution | execution | uncertainty | uncertainty | machine learning | machine learning | linear programming | linear programming | dynamic programming | dynamic programming | integer programming | integer programming | network optimization | network optimization | decision analysis | decision analysis | decision theoretic planning | decision theoretic planning | Markov decision process | Markov decision process | scheme | scheme | propositional logic | propositional logic | constraints | constraints | Markov processes | Markov processes | computational performance | computational performance | satisfaction | satisfaction | learning algorithms | learning algorithms | system state | system state | state | state | search treees | search treees | plan spaces | plan spaces | model theory | model theory | decision trees | decision trees | function approximators | function approximators | optimization algorithms | optimization algorithms | limitations | limitations | tradeoffs | tradeoffs | search and reasoning | search and reasoning | game tree search | game tree search | local stochastic search | local stochastic search | stochastic | stochastic | genetic algorithms | genetic algorithms | constraint satisfaction | constraint satisfaction | propositional inference | propositional inference | rule-based systems | rule-based systems | rule-based | rule-based | model-based diagnosis | model-based diagnosis | neural nets | neural nets | reinforcement learning | reinforcement learning | web-based | web-based | search trees | search trees

License

Content within individual OCW courses is (c) by the individual authors unless otherwise noted. MIT OpenCourseWare materials are licensed by the Massachusetts Institute of Technology under a Creative Commons License (Attribution-NonCommercial-ShareAlike). For further information see http://ocw.mit.edu/terms/index.htm

Site sourced from

http://ocw.mit.edu/rss/all/mit-allarchivedcourses.xml

Attribution

Click to get HTML | Click to get attribution | Click to get URL

All metadata

See all metadata

2.997 Decision Making in Large Scale Systems (MIT) 2.997 Decision Making in Large Scale Systems (MIT)

Description

This course is an introduction to the theory and application of large-scale dynamic programming. Topics include Markov decision processes, dynamic programming algorithms, simulation-based algorithms, theory and algorithms for value function approximation, and policy search methods. The course examines games and applications in areas such as dynamic resource allocation, finance and queueing networks. This course is an introduction to the theory and application of large-scale dynamic programming. Topics include Markov decision processes, dynamic programming algorithms, simulation-based algorithms, theory and algorithms for value function approximation, and policy search methods. The course examines games and applications in areas such as dynamic resource allocation, finance and queueing networks.

Subjects

algorithm | algorithm | markov decision process | markov decision process | dynamic programming | dynamic programming | stochastic models | stochastic models | policy iteration | policy iteration | Q-Learning | Q-Learning | reinforcement learning | reinforcement learning | Lyapunov function | Lyapunov function | ODE | ODE | TD-Learning | TD-Learning | value function approximation | value function approximation | linear programming | linear programming | policy search | policy search | policy gradient | policy gradient | actor-critic | actor-critic | experts algorithm | experts algorithm | regret minimization and calibration | regret minimization and calibration | games. | games.

License

Content within individual OCW courses is (c) by the individual authors unless otherwise noted. MIT OpenCourseWare materials are licensed by the Massachusetts Institute of Technology under a Creative Commons License (Attribution-NonCommercial-ShareAlike). For further information see http://ocw.mit.edu/terms/index.htm

Site sourced from

http://ocw.mit.edu/rss/all/mit-allcourses.xml

Attribution

Click to get HTML | Click to get attribution | Click to get URL

All metadata

See all metadata

MAS.622J Pattern Recognition and Analysis (MIT) MAS.622J Pattern Recognition and Analysis (MIT)

Description

This class deals with the fundamentals of characterizing and recognizing patterns and features of interest in numerical data. We discuss the basic tools and theory for signal understanding problems with applications to user modeling, affect recognition, speech recognition and understanding, computer vision, physiological analysis, and more. We also cover decision theory, statistical classification, maximum likelihood and Bayesian estimation, nonparametric methods, unsupervised learning and clustering. Additional topics on machine and human learning from active research are also talked about in the class. This class deals with the fundamentals of characterizing and recognizing patterns and features of interest in numerical data. We discuss the basic tools and theory for signal understanding problems with applications to user modeling, affect recognition, speech recognition and understanding, computer vision, physiological analysis, and more. We also cover decision theory, statistical classification, maximum likelihood and Bayesian estimation, nonparametric methods, unsupervised learning and clustering. Additional topics on machine and human learning from active research are also talked about in the class.

Subjects

MAS.622 | MAS.622 | 1.126 | 1.126 | pattern recognition | pattern recognition | feature detection | feature detection | classification | classification | probability theory | probability theory | pattern analysis | pattern analysis | conditional probability | conditional probability | bayes rule | bayes rule | random vectors | decision theory | random vectors | decision theory | ROC curves | ROC curves | likelihood ratio test | likelihood ratio test | fisher discriminant | fisher discriminant | template-based recognition | template-based recognition | feature extraction | feature extraction | eigenvector and multilinear analysis | eigenvector and multilinear analysis | linear discriminant | linear discriminant | perceptron learning | perceptron learning | optimization by gradient descent | optimization by gradient descent | support vecotr machines | support vecotr machines | K-nearest-neighbor classification | K-nearest-neighbor classification | parzen estimation | parzen estimation | unsupervised learning | unsupervised learning | clustering | clustering | vector quantization | vector quantization | K-means | K-means | Expectation-Maximization | Expectation-Maximization | Hidden markov models | Hidden markov models | viterbi algorithm | viterbi algorithm | Baum-Welch algorithm | Baum-Welch algorithm | linear dynamical systems | linear dynamical systems | Kalman filtering | Kalman filtering | Bayesian networks | Bayesian networks | decision trees | decision trees | reinforcement learning | reinforcement learning | genetic algorithms | genetic algorithms

License

Content within individual OCW courses is (c) by the individual authors unless otherwise noted. MIT OpenCourseWare materials are licensed by the Massachusetts Institute of Technology under a Creative Commons License (Attribution-NonCommercial-ShareAlike). For further information see http://ocw.mit.edu/terms/index.htm

Site sourced from

http://ocw.mit.edu/rss/all/mit-allcourses-MAS.xml

Attribution

Click to get HTML | Click to get attribution | Click to get URL

All metadata

See all metadata

2.997 Decision Making in Large Scale Systems (MIT)

Description

This course is an introduction to the theory and application of large-scale dynamic programming. Topics include Markov decision processes, dynamic programming algorithms, simulation-based algorithms, theory and algorithms for value function approximation, and policy search methods. The course examines games and applications in areas such as dynamic resource allocation, finance and queueing networks.

Subjects

algorithm | markov decision process | dynamic programming | stochastic models | policy iteration | Q-Learning | reinforcement learning | Lyapunov function | ODE | TD-Learning | value function approximation | linear programming | policy search | policy gradient | actor-critic | experts algorithm | regret minimization and calibration | games.

License

Content within individual OCW courses is (c) by the individual authors unless otherwise noted. MIT OpenCourseWare materials are licensed by the Massachusetts Institute of Technology under a Creative Commons License (Attribution-NonCommercial-ShareAlike). For further information see https://ocw.mit.edu/terms/index.htm

Site sourced from

https://ocw.mit.edu/rss/all/mit-allsimplifiedchinesecourses.xml

Attribution

Click to get HTML | Click to get attribution | Click to get URL

All metadata

See all metadata

16.410 Principles of Autonomy and Decision Making (MIT)

Description

This course surveys a variety of reasoning, optimization, and decision-making methodologies for creating highly autonomous systems and decision support aids. The focus is on principles, algorithms, and their applications, taken from the disciplines of artificial intelligence and operations research. Reasoning paradigms include logic and deduction, heuristic and constraint-based search, model-based reasoning, planning and execution, reasoning under uncertainty, and machine learning. Optimization paradigms include linear, integer and dynamic programming. Decision-making paradigms include decision theoretic planning, and Markov decision processes. This course is offered both to undergraduate (16.410) students as a professional area undergraduate subject, in the field of aerospace information

Subjects

autonomy | decision | decision-making | reasoning | optimization | autonomous | autonomous systems | decision support | algorithms | artificial intelligence | a.i. | operations | operations research | logic | deduction | heuristic search | constraint-based search | model-based reasoning | planning | execution | uncertainty | machine learning | linear programming | dynamic programming | integer programming | network optimization | decision analysis | decision theoretic planning | Markov decision process | scheme | propositional logic | constraints | Markov processes | computational performance | satisfaction | learning algorithms | system state | state | search treees | plan spaces | model theory | decision trees | function approximators | optimization algorithms | limitations | tradeoffs | search and reasoning | game tree search | local stochastic search | stochastic | genetic algorithms | constraint satisfaction | propositional inference | rule-based systems | rule-based | model-based diagnosis | neural nets | reinforcement learning | web-based | search trees

License

Content within individual OCW courses is (c) by the individual authors unless otherwise noted. MIT OpenCourseWare materials are licensed by the Massachusetts Institute of Technology under a Creative Commons License (Attribution-NonCommercial-ShareAlike). For further information see https://ocw.mit.edu/terms/index.htm

Site sourced from

https://ocw.mit.edu/rss/all/mit-allarchivedcourses.xml

Attribution

Click to get HTML | Click to get attribution | Click to get URL

All metadata

See all metadata

16.410 Principles of Autonomy and Decision Making (MIT)

Description

This course surveys a variety of reasoning, optimization, and decision-making methodologies for creating highly autonomous systems and decision support aids. The focus is on principles, algorithms, and their applications, taken from the disciplines of artificial intelligence and operations research. Reasoning paradigms include logic and deduction, heuristic and constraint-based search, model-based reasoning, planning and execution, reasoning under uncertainty, and machine learning. Optimization paradigms include linear, integer and dynamic programming. Decision-making paradigms include decision theoretic planning, and Markov decision processes. This course is offered both to undergraduate (16.410) students as a professional area undergraduate subject, in the field of aerospace information

Subjects

autonomy | decision | decision-making | reasoning | optimization | autonomous | autonomous systems | decision support | algorithms | artificial intelligence | a.i. | operations | operations research | logic | deduction | heuristic search | constraint-based search | model-based reasoning | planning | execution | uncertainty | machine learning | linear programming | dynamic programming | integer programming | network optimization | decision analysis | decision theoretic planning | Markov decision process | scheme | propositional logic | constraints | Markov processes | computational performance | satisfaction | learning algorithms | system state | state | search treees | plan spaces | model theory | decision trees | function approximators | optimization algorithms | limitations | tradeoffs | search and reasoning | game tree search | local stochastic search | stochastic | genetic algorithms | constraint satisfaction | propositional inference | rule-based systems | rule-based | model-based diagnosis | neural nets | reinforcement learning | web-based | search trees

License

Content within individual OCW courses is (c) by the individual authors unless otherwise noted. MIT OpenCourseWare materials are licensed by the Massachusetts Institute of Technology under a Creative Commons License (Attribution-NonCommercial-ShareAlike). For further information see https://ocw.mit.edu/terms/index.htm

Site sourced from

https://ocw.mit.edu/rss/all/mit-allarchivedcourses.xml

Attribution

Click to get HTML | Click to get attribution | Click to get URL

All metadata

See all metadata

2.997 Decision Making in Large Scale Systems (MIT)

Description

This course is an introduction to the theory and application of large-scale dynamic programming. Topics include Markov decision processes, dynamic programming algorithms, simulation-based algorithms, theory and algorithms for value function approximation, and policy search methods. The course examines games and applications in areas such as dynamic resource allocation, finance and queueing networks.

Subjects

algorithm | markov decision process | dynamic programming | stochastic models | policy iteration | Q-Learning | reinforcement learning | Lyapunov function | ODE | TD-Learning | value function approximation | linear programming | policy search | policy gradient | actor-critic | experts algorithm | regret minimization and calibration | games.

License

Content within individual OCW courses is (c) by the individual authors unless otherwise noted. MIT OpenCourseWare materials are licensed by the Massachusetts Institute of Technology under a Creative Commons License (Attribution-NonCommercial-ShareAlike). For further information see https://ocw.mit.edu/terms/index.htm

Site sourced from

https://ocw.mit.edu/rss/all/mit-allcourses.xml

Attribution

Click to get HTML | Click to get attribution | Click to get URL

All metadata

See all metadata

MAS.622J Pattern Recognition and Analysis (MIT)

Description

This class deals with the fundamentals of characterizing and recognizing patterns and features of interest in numerical data. We discuss the basic tools and theory for signal understanding problems with applications to user modeling, affect recognition, speech recognition and understanding, computer vision, physiological analysis, and more. We also cover decision theory, statistical classification, maximum likelihood and Bayesian estimation, nonparametric methods, unsupervised learning and clustering. Additional topics on machine and human learning from active research are also talked about in the class.

Subjects

MAS.622 | 1.126 | pattern recognition | feature detection | classification | probability theory | pattern analysis | conditional probability | bayes rule | random vectors | decision theory | ROC curves | likelihood ratio test | fisher discriminant | template-based recognition | feature extraction | eigenvector and multilinear analysis | linear discriminant | perceptron learning | optimization by gradient descent | support vecotr machines | K-nearest-neighbor classification | parzen estimation | unsupervised learning | clustering | vector quantization | K-means | Expectation-Maximization | Hidden markov models | viterbi algorithm | Baum-Welch algorithm | linear dynamical systems | Kalman filtering | Bayesian networks | decision trees | reinforcement learning | genetic algorithms

License

Content within individual OCW courses is (c) by the individual authors unless otherwise noted. MIT OpenCourseWare materials are licensed by the Massachusetts Institute of Technology under a Creative Commons License (Attribution-NonCommercial-ShareAlike). For further information see https://ocw.mit.edu/terms/index.htm

Site sourced from

https://ocw.mit.edu/rss/all/mit-allcourses.xml

Attribution

Click to get HTML | Click to get attribution | Click to get URL

All metadata

See all metadata