Kickstarting Deep Reinforcement Learning.
Simon SchmittJonathan J. HudsonAugustin ZídekSimon OsinderoCarl DoerschWojciech M. CzarneckiJoel Z. LeiboHeinrich KüttlerAndrew ZissermanKaren SimonyanS. M. Ali EslamiPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- machine learning
- multi agent
- markov decision processes
- deep learning
- control problems
- reward function
- model free
- state space
- learning problems
- robot control
- temporal difference learning
- bayesian networks
- policy search
- real time
- function approximators
- direct policy search
- transition model
- robotic control
- transfer learning
- optimal policy
- unsupervised learning
- learning process
- support vector
- decision trees
- website
- databases