Pembelajaran pengukuhan
Penampilan
Berinspirasikan psikologi tingkah laku, pembelajaran pengukuhan ialah satu kawasan pembelajaran mesin dan sains komputer, mengenai cara satu agen akan mengambil tindakan dalam satu persekitaran untuk memaksimumkan sesetengah tanggapan ganjaran longgokan.
Rujukan
[sunting | sunting sumber]Pautan luar
[sunting | sunting sumber]- Reinforcement Learning Repository (Inggeris)
- Reinforcement Learning and Artificial Intelligence Diarkibkan 2019-02-07 di Wayback Machine (Sutton's lab at the University of Alberta)
- (Inggeris) Upah Gaji
- (Inggeris) Nguliday
- Autonomous Learning Laboratory (Barto's lab at the University of Massachusetts Amherst) (Inggeris)
- RL-Glue (Inggeris)
- Software Tools for Reinforcement Learning (Matlab and Python) Diarkibkan 2013-07-21 di Wayback Machine (Inggeris)
- The UofA Reinforcement Learning Library (texts) Diarkibkan 2012-02-06 di Wayback Machine (Inggeris)
- The Reinforcement Learning Toolbox from the (Graz University of Technology) (Inggeris)
- Hybrid reinforcement learning Diarkibkan 2019-08-18 di Wayback Machine (Inggeris)
- Piqle: a Generic Java Platform for Reinforcement Learning (Inggeris)
- A Short Introduction To Some Reinforcement Learning Algorithms Diarkibkan 2010-06-12 di Wayback Machine (Inggeris)
- Reinforcement Learning applied to Tic-Tac-Toe Game Diarkibkan 2016-08-28 di Wayback Machine (Inggeris)
- Scholarpedia Reinforcement Learning (Inggeris)
- Scholarpedia Temporal Difference Learning (Inggeris)
- Stanford Reinforcement Learning Course Diarkibkan 2012-03-21 di Wayback Machine (Inggeris)
- Real-world reinforcement learning experiments Diarkibkan 2018-10-08 di Wayback Machine at Delft University of Technology (Inggeris)
- Reinforcement Learning Tools for Matlab (Inggeris)
- Stanford University Andrew Ng Lecture on Reinforcement Learning (Inggeris)
Jika anda melihat rencana yang menggunakan templat {{tunas}} ini, gantikanlah dengan templat tunas yang lebih spesifik.