Deep Reinforcement Learning with Double Q-learning.
Hado van HasseltArthur GuezDavid SilverPublished in: CoRR (2015)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- optimal policy
- state space
- state action space
- temporal difference learning
- multi agent
- markov decision processes
- action selection
- stochastic approximation
- learning algorithm
- multi agent reinforcement learning
- control problems
- learning process
- temporal difference
- eligibility traces
- dynamic programming
- supervised learning
- reinforcement learning methods
- machine learning
- continuous state and action spaces
- rl algorithms
- partially observable
- state action
- function approximators
- continuous state
- learning agent
- continuous state spaces
- reinforcement learning problems
- relational reinforcement learning
- reward function
- optimal control