ConceptAI & ML
Value iteration
An algorithm that uses the Bellman equation as an iterative update to find the optimal Q-function.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Fitted value iteration2Asynchronous dynamic programming1Curse of dimensionality1Discount factor in value iteration1Fitted value iteration with analytical minimization1Model-based learning1Model-based reinforcement learning1Neural fitted value iteration1Optimism problem1Planning with a model1Policy evaluation1Policy iteration1
Lecturers
6Each in their own terms, from the easiest level.
Russ Tedrake
An iterative algorithm based on the Bellman equation to find the optimal cost-to-go and policy over an infinite horizon.Pieter Abbeel
An algorithm that computes optimal values by starting at the bottom of the search tree and working upward iteratively.David Silver
An iterative algorithm that applies the Bellman optimality equation as an update rule to find the optimal value function by working backwards from the goal.Pieter Abbeel & Daniel Klein
A backward pass over a trajectory to find the optimal sequence of feedback controllers.Sergey Levine
An algorithm that short-circuits policy iteration by updating Q-values and directly taking the maximum over actions to compute the value function.
Lectures that assume it
6Connections
25The lectures that define it or assume it, and the concepts next to it.
Concepts10
Lectures15
- Markov Decision Processes (MDPs) Part 1/2
- Planning by Dynamic Programming — Policy & Value Iteration
- Dynamic Programming I
- Markov Decision Processes (MDPs) Part 2/2
- Foundational concepts in deep reinforcement learning
- Dynamic Programming III
Show 9 moreShow fewer
- Stochastic Control
- Deep Reinforcement Learning
- Robotics, Language, and Vision
- Reinforcement Learning Part 1/2
- Exploration of fundamental concepts in deep reinforcement learning
- Control as Inference, Part 3
- Integrating Learning and Planning
- Exploration of deep reinforcement learning architectures and algorithms
- Reinforcement Learning Part 2/2