j

java-ai-minefield-navigator

TD-FALCON is a fusion architecture that incorporates temporal difference methods and self-organizing neural networks for reinforcement learning with delayed rewards. It learns by creating cognitive codes across sensory input, actions, and rewards.
https://github.com/cschen1205/java-ai-minefield-navigator
MIT
Caishun Chen
incorporates methods organizing neural self architecture across fusion networks creating with delayed rewards learning difference that cognitive input sensory temporal learns falcon codes reinforcement actions
Aggregated version Version Update time
1.0 1.0.2 Jun 18, 2017
1.0.1 Jun 06, 2017
2 Records