ConceptAI & ML
Reward
The equivalent of costs from search in MDPs, received as big rewards at the end or small living rewards each step.
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
2Each in their own terms, from the easiest level.
David Silver
A scalar feedback signal that indicates how well the agent is doing at step .
Lectures that assume it
11- Model-Free Control — ε-Greedy SARSA & Off-Policy Q-Learning
- Natural Policy Gradients, Covariant Updates & The Fisher Information Matrix
- Decision Transformer: Reinforcement Learning via Sequence Modeling
- Exploration and Exploitation
- Introduction to Reinforcement Learning (CS234, 2024, Lecture 1)
- Compiler 2.0: Building the Next Generation of Compilers with Machine Learning
- Foundational concepts in deep reinforcement learning
- Policy Gradient Methods
- Deep Reinforcement Learning
- Actor-Critic Methods: Value Function Bootstrapping & Advantage Estimation
- Exploration of fundamental concepts in deep reinforcement learning
Connections
20The lectures that define it or assume it, and the concepts next to it.
Concepts7
Show 1 moreShow fewer
Lectures13
- Introduction to Reinforcement Learning
- Markov Decision Processes (MDPs) Part 1/2
- Model-Free Control — ε-Greedy SARSA & Off-Policy Q-Learning
- Natural Policy Gradients, Covariant Updates & The Fisher Information Matrix
- Decision Transformer: Reinforcement Learning via Sequence Modeling
- Exploration and Exploitation
Show 7 moreShow fewer
- Introduction to Reinforcement Learning (CS234, 2024, Lecture 1)
- Compiler 2.0: Building the Next Generation of Compilers with Machine Learning
- Foundational concepts in deep reinforcement learning
- Policy Gradient Methods
- Deep Reinforcement Learning
- Actor-Critic Methods: Value Function Bootstrapping & Advantage Estimation
- Exploration of fundamental concepts in deep reinforcement learning