Deep Reinforcement Learning Nanodegree Program
Deep Reinforcement Learning Nanodegree Program Online Course.
The Deep Reinforcement Learning Nanodegree has four courses: Introduction to Deep Reinforcement Learning, Value-Based Methods, Policy-Based Methods, and Multi-Agent RL. Students learn to implement classical solution methods, define Markov decision processes, policies, and value functions, and derive Bellman equations. They learn dynamic programming, Monte Carlo methods, temporal-difference methods, deep RL, and apply these techniques to solve real-world problems. They learn to train agents to navigate virtual worlds, generate optimal financial trading strategies, and apply RL to multiple interacting agents.
Skills you’ll learn:
Introduction to Deep Reinforcement Learning
Exploration-exploitation dilemma • Markov decision processes • Multi-armed bandit problems • Bellman equation • Policy-based reinforcement learning • Continuous functions • Value-based reinforcement learning • Monte carlo methods • Dynamic programming
Value-Based Methods
Value-based reinforcement learning • Prioritized experience replay • Deep q-networks • Double deep q-networks • Dueling deep q-networks
Policy-Based Methods
Stochastic policy gradients • Reinforce algorithm • Policy optimization algorithms • Evolutionary algorithms • Monte carlo policy gradients • Generalized advantage estimation
Multi-Agent Reinforcement Learning
Multi-agent training • Markov games • Alphazero
Prerequisite Details
To optimize your success in this program, we’ve created a list of prerequisites and recommendations to help you prepare for the curriculum. Prior to enrolling, you should have the following knowledge:
- Intermediate Python
- Deep learning framework proficiency
- Neural network basics
- Object-oriented programming basics
- Reinforcement learning fundamentals
You will also need to be able to communicate fluently and professionally in written and spoken English.
