Commit History

Autor SHA1 Mensaxe Data
  Martin Thoma ddd08a2a45 Improve pseudocode %!s(int64=9) %!d(string=hai) anos
  Martin Thoma dd9390388d Add protocol %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 1f5881a6e0 Add normal-distribution-z %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 45e56d0320 Improve pseudocode %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 14e85b383e Improve pseudocode %!s(int64=9) %!d(string=hai) anos
  Martin Thoma f9cdad4e4f Fix label correction pseudocode %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 4e5cdcde51 Fix pseudocode %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 27a1325e83 Fix Dyna-q %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 30c37862a8 Add dyna-q algorithm %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 578245c784 Fix pseudocode %!s(int64=9) %!d(string=hai) anos
  Martin Thoma c0bbfa6811 Add q-lambda %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 93fc9e52ed Add sarsa lambda pseudocode %!s(int64=9) %!d(string=hai) anos
  Martin Thoma ea63ce4d57 Not learning rate but discount factor %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 2ec24b14b8 Add XOR problem graphic %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 0085bb50d5 Add return value %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 1c54ccd821 Fix error in label correction; extend for banch-and-bound %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 001350bae4 Add q-learning and improve value iteration pseudocode %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 807b9268d0 Improve quality of description %!s(int64=9) %!d(string=hai) anos
  Martin Thoma b9e2162ab8 Add dynamic programming and label correction algorithm %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 940436c883 Update pseudocode to include cost function as parameter %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 23462814aa Slant text to arrow %!s(int64=9) %!d(string=hai) anos
  Martin Thoma f4674abc32 Make Kalman filter formulas more memorizable %!s(int64=9) %!d(string=hai) anos
  Martin Thoma d65f5d2933 Add pseudocode for policy- and value-iteration %!s(int64=9) %!d(string=hai) anos
  Martin Thoma fc8c41330a Add agent environment diagram for RL %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 2a2e2d1a88 Rename MDP, POMDP %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 73be14bd67 Mention requirements %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 37aa7c4ecb Update README %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 5400ce8e04 Add elevation chart %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 41896e3668 Add pomdp scheme %!s(int64=9) %!d(string=hai) anos
  Martin Thoma 868f09c3ae Add MDP schema %!s(int64=9) %!d(string=hai) anos