Artificial Intelligence · Reinforcement Learning
A topic within Reinforcement Learning, itself one of 11 topics in that field and part of Artificial Intelligence.
2 works
Mnih et al.
Shows that running many actor-learners asynchronously on CPU cores stabilises deep reinforcement learning as well as a replay buffer does, while training faster and off GPU.
link checked 17 Sept 2026Konda & Tsitsiklis
Gives the first convergence proof for actor-critic methods with function approximation, showing the critic's approximation error does not derail the actor as long as it is compatible with the policy gradient.
link checked 17 Sept 2026