Unterschiede
Hier werden die Unterschiede zwischen zwei Versionen der Seite angezeigt.
| Nächste Überarbeitung | Vorherige Überarbeitung | ||
| ef_informatik:machine-learning [2022-02-07 10:46] – angelegt hof | ef_informatik:machine-learning [2022-03-29 09:58] (aktuell) – [Syllabus] hof | ||
|---|---|---|---|
| Zeile 14: | Zeile 14: | ||
| * Immediate reward given by game score (points) | * Immediate reward given by game score (points) | ||
| * Q-Function is a table (Q-Table) dynamically updated by Bellman-formula | * Q-Function is a table (Q-Table) dynamically updated by Bellman-formula | ||
| - | * Hidden Markov Models | + | * Hidden Markov Models |
| * -> what if we cannot observe all the internal state? | * -> what if we cannot observe all the internal state? | ||
| - | * -> infer probability of hidden (latent) state from observations | + | * -> infer probability of hidden (latent) state from observations |
| - | * Reinforcement Learning | + | * Deep Reinforcement Learning |
| * Q-Function is not a table, but a neural network, which is trained by repeatedly running the game and updating the neuron states. | * Q-Function is not a table, but a neural network, which is trained by repeatedly running the game and updating the neuron states. | ||
| - | * builds on top of sca's NN week | + | * builds on top of [[neuronales_netzwerk_handschrift: |
| + | * Prereqs: | ||
| + | * OpenAI Gym environment: | ||
| + | * keras / tensorflow? | ||
hof