Skip to content

Latest commit

 

History

History
2 lines (2 loc) · 336 Bytes

File metadata and controls

2 lines (2 loc) · 336 Bytes

GDG QAADA: Discover Reinforcement Learning

An introduction into the reinforcement learning framework (agent, environment, state, reward, action) and some fundamental concepts (Markov Decision Process, Bellman Equation, Temporal Difference Learning...) alongside an implementation of a simple navigation agent with Q-Learning algorithm