Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- learning algorithm
- continuous state and action spaces
- state space
- action selection
- eligibility traces
- multi agent
- optimal policy
- temporal difference learning
- multi agent reinforcement learning
- function approximators
- markov decision processes
- control problems
- dynamic programming
- state action space
- stochastic approximation
- machine learning
- learning process
- partially observable
- markov decision process
- learning agent
- temporal difference
- policy iteration
- state action
- learning agents
- optimal control
- learning problems
- approximate dynamic programming
- transfer learning
- supervised learning
- neural network