Model-Based Stabilisation of Deep Reinforcement Learning.
Felix LeibfriedRasul TutunovPeter VrancxHaitham Bou-AmmarPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- model free
- function approximation
- reinforcement learning algorithms
- machine learning
- learning algorithm
- artificial intelligence
- multi agent
- data sets
- real time
- temporal difference learning
- state space
- stochastic approximation
- temporal difference
- optimal policy
- decision making
- dynamic programming
- optimal control
- hidden markov models
- artificial neural networks
- deep learning
- search engine
- reinforcement learning methods
- databases