Commit History

Author SHA1 Message Date
  Martin Thoma 79d861fffe Add image 9 years ago
  Martin Thoma 4e7bec12b0 Add rendered version 9 years ago
  Martin Thoma ed17f4290a Add PDF 9 years ago
  Martin Thoma acd54112b1 Add Informationsfusion 9 years ago
  Martin Thoma 6bdd873a8a Update slides 9 years ago
  Martin Thoma b5cb0e67f0 Add sommerakademie 9 years ago
  Martin Thoma ddd08a2a45 Improve pseudocode 9 years ago
  Martin Thoma dd9390388d Add protocol 9 years ago
  Martin Thoma 1f5881a6e0 Add normal-distribution-z 9 years ago
  Martin Thoma 45e56d0320 Improve pseudocode 9 years ago
  Martin Thoma 14e85b383e Improve pseudocode 9 years ago
  Martin Thoma f9cdad4e4f Fix label correction pseudocode 9 years ago
  Martin Thoma 4e5cdcde51 Fix pseudocode 9 years ago
  Martin Thoma 27a1325e83 Fix Dyna-q 9 years ago
  Martin Thoma 30c37862a8 Add dyna-q algorithm 9 years ago
  Martin Thoma 578245c784 Fix pseudocode 9 years ago
  Martin Thoma c0bbfa6811 Add q-lambda 9 years ago
  Martin Thoma 93fc9e52ed Add sarsa lambda pseudocode 9 years ago
  Martin Thoma ea63ce4d57 Not learning rate but discount factor 9 years ago
  Martin Thoma 2ec24b14b8 Add XOR problem graphic 9 years ago
  Martin Thoma 0085bb50d5 Add return value 9 years ago
  Martin Thoma 1c54ccd821 Fix error in label correction; extend for banch-and-bound 9 years ago
  Martin Thoma 001350bae4 Add q-learning and improve value iteration pseudocode 10 years ago
  Martin Thoma 807b9268d0 Improve quality of description 10 years ago
  Martin Thoma b9e2162ab8 Add dynamic programming and label correction algorithm 10 years ago
  Martin Thoma 940436c883 Update pseudocode to include cost function as parameter 10 years ago
  Martin Thoma 23462814aa Slant text to arrow 10 years ago
  Martin Thoma f4674abc32 Make Kalman filter formulas more memorizable 10 years ago
  Martin Thoma d65f5d2933 Add pseudocode for policy- and value-iteration 10 years ago
  Martin Thoma fc8c41330a Add agent environment diagram for RL 10 years ago