AdvancedAdvanced
Reinforcement Learning
Build agents that learn by doing. This advanced course covers Markov decision processes, Q-learning and policy-gradient methods, culminating in agents that can play games.
8 weeks4.7 rating680 enrolled
What you'll learn
Model problems as MDPs
Implement Q-learning
Apply policy-gradient methods
Train game-playing agents
Curriculum
1
RL Foundations
- Markov decision processes
- Rewards & value functions
- Exploration vs exploitation
2
Value Methods
- Q-learning
- Deep Q-networks
- Experience replay
3
Policy Methods
- Policy gradients
- Actor-critic
- Game-playing agents
Tools you'll master
PythonPyTorchGymnasiumStable-Baselines3
$1,299One payment, lifetime access
Duration8 weeks
LevelAdvanced
CertificateIncluded
Career supportIncluded
30-day money-back guarantee
Ready to Start Your Tech Career?
Join thousands of graduates who transformed their careers with us. Your future in AI, cloud and cybersecurity starts here.