ConceptAI & ML
Actor-critic algorithm
An algorithm that combines policy optimization (actor) with value function estimation (critic).
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.
Fei-Fei Li, Justin Johnson & Serena Yeung
A reinforcement learning method that combines policy gradients (the actor) and Q-learning (the critic) to learn both a policy and a value function.
Lectures that assume it
6Connections
16The lectures that define it or assume it, and the concepts next to it.
Concepts8
- Policy gradient
- Policy evaluation
- Q-learning
- Continual actor-critic control
- Explicit policy constraint methods
- Off-policy actor-critic
Show 2 moreShow fewer
Lectures8
- Trust Region Policy Optimization (TRPO) & Monotonic Policy Improvement
- Deep Reinforcement Learning
- Exploration of fundamental concepts in deep reinforcement learning
- Offline Reinforcement Learning II
- The Alberta Plan for AI Research: Continual Reinforcement Learning
- Frontiers of Deep Reinforcement Learning