AI engineering glossary · Reinforcement learning
What is a3C?
A3C (also called Asynchronous advantage actor-critic): An actor-critic method in which many workers run in parallel on separate copies of the world and update shared parameters asynchronously. It made deep policy learning feasible on ordinary CPUs and decorrelates data without a replay buffer.
A3C: an example
16 CPU threads each run an environment and push gradients to a shared network.
Related terms
More Reinforcement learning terms
- Action-value function
- Actor-critic
- Agent
- AlphaGo
- AlphaZero
- Baseline (policy gradient)
- Behavioural cloning
- Belief state
Where you learn it
A3C is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.