A3C and asynchronous neural actor-learners

What changed

Ran parallel actor-learners with asynchronous gradient updates to decorrelate online experience, developing asynchronous variants of value-learning and advantage actor-critic methods without relying on a replay buffer.

Scientific scope

Ran parallel actor-learners with asynchronous gradient updates to decorrelate online experience, developing asynchronous variants of value-learning and advantage actor-critic methods without relying on a replay buffer. The method builds on actor-critic learning, temporal-difference updates and distributed computation. Reported CPU-training, game and control gains apply to the tested configurations; they are not a global convergence guarantee for arbitrary nonlinear policies.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. The method builds on actor-critic learning, temporal-difference updates and distributed computation. Reported CPU-training, game and control gains apply to the tested configurations; they are not a global convergence guarantee for arbitrary nonlinear policies.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Asynchronous Methods for Deep Reinforcement Learning

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction