ConceptAI & ML
Policy optimization
The problem of finding policy parameters that maximize the policy objective 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.
Lecturers
1Lectures that assume it
7- POPRi: Private Federated Learning using Preference-Optimized Synthetic Data
- Simulation-Driven Robot Learning for the Lazy Researcher
- Reinforcement Learning from Human Feedback: Algorithms & Applications
- Model-Based Reinforcement Learning with Policies
- RL with Sequence Models & Language Models, Part 1 (CS 285, Lecture 21)
- Overview of Transformers (Stanford CS25: Transformers United V6)
- Guest Lecture: Aviral Kumar (UC Berkeley CS 285)
Connections
15The lectures that define it or assume it, and the concepts next to it.
Concepts7
- Optimization
- Policy objective functions
- Direct preference optimization
- Group relative policy optimization
- Information-gathering actions
- KL divergence penalty in RL
Show 1 moreShow fewer
Lectures8
- Policy Gradient Methods
- POPRi: Private Federated Learning using Preference-Optimized Synthetic Data
- Simulation-Driven Robot Learning for the Lazy Researcher
- Reinforcement Learning from Human Feedback: Algorithms & Applications
- Model-Based Reinforcement Learning with Policies
- RL with Sequence Models & Language Models, Part 1 (CS 285, Lecture 21)