Deep Reinforcement Learning with Double Q-Learning.
Hado van HasseltArthur GuezDavid SilverPublished in: AAAI (2016)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- model free
- temporal difference learning
- state action space
- markov decision processes
- optimal policy
- control problems
- learning algorithm
- learning problems
- eligibility traces
- stochastic approximation
- multi agent
- action selection
- temporal difference
- cooperative
- multi agent reinforcement learning
- continuous state
- policy iteration
- learning agent
- dynamic programming
- approximate dynamic programming
- relational reinforcement learning
- continuous state and action spaces
- supervised learning
- average reward
- partially observable
- policy gradient
- reward function
- actor critic
- policy search
- learning classifier systems