ConceptAI & ML
Policy
The agent's behavior function mapping states to actions.
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.
Lecturers
8Each in their own terms, from the easiest level.
David Silver
A distribution over actions given states that fully defines the behavior of an agent.Pieter Abbeel
A mapping from states to actions that dictates what an agent should do in any given state.Emma Brunskill
A mapping from states to actions that defines the behavior of an agent.Fei-Fei Li, Justin Johnson & Serena Yeung
A function from states to actions that specifies what action to take in each state.Russ Tedrake
A function that maps states to control actions.Sergey Levine
A distribution over actions conditional on observations or states.Leslie Kaelbling
A closed-loop controller that takes the system from one state to another.Max Simchowitz
A mapping from states to distributions over actions that describes what an agent does.
Lectures that assume it
15The first 12 are shown.
- Planning by Dynamic Programming — Policy & Value Iteration
- Adversarial Examples and Adversarial Training
- Natural Policy Gradients, Covariant Updates & The Fisher Information Matrix
- Deep Reinforcement Learning
- Reinforcement Learning Part 1/2
- Decision Transformer: Reinforcement Learning via Sequence Modeling
- Offline Reinforcement Learning II
- Classic Games
- Challenges & Open Problems in Deep Reinforcement Learning
- Policy Gradient Methods
- Integrating Learning and Planning
- Transfer Learning & Meta-Learning
Connections
35The lectures that define it or assume it, and the concepts next to it.
Concepts9
Show 3 moreShow fewer
Lectures26
- Introduction to Reinforcement Learning
- Markov Processes, Reward Processes & Bellman Equations
- Markov Decision Processes (MDPs) Part 1/2
- Introduction to Reinforcement Learning (CS234, 2024, Lecture 1)
- Dynamic Programming I
- Policy Gradient Foundations: Trajectory Distributions & High-Dimensional State Spaces
Show 20 moreShow fewer
- Markov Decision Processes (MDPs) Part 2/2
- The Role of Rationality in Modern Robotics
- Imitation Learning I: Behavioral Cloning & Distributional Shift
- Deep Reinforcement Learning
- Generative Control, Action Chunking, and Moravec’s Paradox
- Planning by Dynamic Programming — Policy & Value Iteration
- Adversarial Examples and Adversarial Training
- Natural Policy Gradients, Covariant Updates & The Fisher Information Matrix
- Deep Reinforcement Learning
- Reinforcement Learning Part 1/2
- Decision Transformer: Reinforcement Learning via Sequence Modeling
- Offline Reinforcement Learning II
- Classic Games
- Challenges & Open Problems in Deep Reinforcement Learning
- Policy Gradient Methods
- Integrating Learning and Planning
- Transfer Learning & Meta-Learning
- Reinforcement Learning Part 2/2
- Imitation Learning, Foundation Models, and Course Wrap-up
- Sequential Optimization of Dynamically Augmented Conditional Value-at-Risk