Skip to main content
grasp.study
About
Explore
Pricing
Log in
Try it for free
Back to course
👋
Welcome to a Grasp lesson
Create a free account
to keep studying and create your own study path.
Generative AI for Autonomous Driving
·
Module 7
Reinforcement Learning Foundations
1
Introduction to Markov Decision Processes
Define the components of a Markov Decision Process: states, actions, transition dynamics, and rewards
Stochastic Policies and Action Probability Distributions
Explain stochastic policies and how they define probability distributions over actions
3
Understanding Value Functions: V(s) and Q(s,a)
Define the state-value function V(s) and the action-value function Q(s,a)
4
The Policy Gradient Theorem: Derivation and Significance
State the policy gradient theorem and explain its significance for optimizing parameterized policies
5
REINFORCE: Policy Gradients with Sampled Returns
Describe the REINFORCE algorithm and how it uses sampled returns to estimate policy gradients
6
Baseline Subtraction for Variance Reduction in Policy Gradients
Explain how subtracting a baseline reduces variance in policy gradient estimates
7
Importance Sampling in Off-Policy Policy Gradients
Describe the importance sampling ratio and its role in off-policy policy gradient methods
Previous module
Scaling with Mixture-of-Experts
Next module
Post-Training Alignment: SFT, PPO, and DPO