Deep Reinforcement Learning: From Q-Learning to Deep Q-Learning.
Fuxiao TanPengfei YanXinping GuanPublished in: ICONIP (4) (2017)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- state space
- optimal policy
- stochastic approximation
- learning algorithm
- action selection
- state action space
- multi agent
- markov decision processes
- multi agent reinforcement learning
- reinforcement learning methods
- continuous state and action spaces
- control problems
- relational reinforcement learning
- dynamic programming
- temporal difference
- policy iteration
- rl algorithms
- temporal difference learning
- function approximators
- machine learning
- state action
- learning process
- learning rate
- learning problems
- deep learning
- cooperative
- reward function
- state abstraction
- supervised learning
- eligibility traces
- transfer learning