ConceptAI & ML
Q-function
The expected sum of future rewards starting from state st, taking action at, and then following policy pi thereafter.
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
1Sergey Levine
Lectures that assume it
11- Natural Policy Gradients, Covariant Updates & The Fisher Information Matrix
- Exploration of fundamental concepts in deep reinforcement learning
- Exploration of advanced topics in deep reinforcement learning
- Foundational concepts in deep reinforcement learning
- Offline Reinforcement Learning
- Offline Reinforcement Learning (CS 285, Lecture 15, Part 3)
- Deep Reinforcement Learning
- Non-parametric Causal Inference in Dynamic Thresholding Designs
- Reinforcement Learning Part 2/2
- Foundational concepts in deep reinforcement learning, likely
- RL Theory
Connections
21The lectures that define it or assume it, and the concepts next to it.
Concepts8
- Markov decision processes
- Expectation
- Policy
- Value function
- Advantage function
- Bellman optimality operator
Show 2 moreShow fewer
Lectures13
- Deep Reinforcement Learning
- Exploration of fundamental concepts in deep reinforcement learning
- Natural Policy Gradients, Covariant Updates & The Fisher Information Matrix
- Exploration of fundamental concepts in deep reinforcement learning
- Exploration of advanced topics in deep reinforcement learning
- Foundational concepts in deep reinforcement learning