Transient Non-stationarity and Generalisation in Deep Reinforcement Learning.
Maximilian IglGregory FarquharJelena LuketinaWendelin BoehmerShimon WhitesonPublished in: ICLR (2021)
Keyphrases
- reinforcement learning
- non stationary
- function approximation
- steady state
- reinforcement learning algorithms
- state space
- markov decision processes
- temporal difference
- direct policy search
- machine learning
- robotic control
- temporal difference learning
- deep learning
- control problems
- model free
- multi agent
- learning algorithm
- optimal policy
- supervised learning
- learning process
- stochastic approximation
- search engine