UCL / DeepMind RL Lecture 1: Introduction to Reinforcement Learning
1:28:12UCL / DeepMind RL Lecture 2: Markov Processes, Reward Processes & Bellman Equations
1:42:04UCL / DeepMind RL Lecture 3: Planning by Dynamic Programming — Policy & Value Iteration
1:39:09UCL / DeepMind RL Lecture 4: Model-Free Prediction — Monte Carlo, TD(0) & TD(λ)
1:37:01UCL / DeepMind RL Lecture 5: Model-Free Control — ε-Greedy SARSA & Off-Policy Q-Learning
1:36:30UCL / DeepMind RL Lecture 6: Value Function Approximation & Deep Q-Networks (DQN)
1:36:45RL Course by David Silver - Lecture 7: Policy Gradient Methods
1:33:58RL Course by David Silver - Lecture 8: Integrating Learning and Planning
1:40:12Lecture 9: Exploration and Exploitation (COMP0089)
1:39:18Lecture 10: Classic Games (COMP0089)
1:51:24Lecture 9: Exploration and Exploitation (COMP0089)
This lecture dissects the fundamental dilemma between exploration and exploitation in reinforcement learning, introducing techniques like epsilon-greedy and upper confidence bound (UCB) algorithms. It examines how these strategies balance discovering new information with leveraging existing knowledge to maximize rewards.
RL Course by David Silver - Lecture 8: Integrating Learning and Planning
Next · Lecture 10Lecture 10: Classic Games (COMP0089)
Seminar notes & discussion
No public seminar notes on this lecture yet.