Heuristically Accelerated Q-Learning: A New Approach to Speed Up Reinforcement Learning.
Reinaldo A. C. BianchiCarlos H. C. RibeiroAnna Helena Reali CostaPublished in: SBIA (2004)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- state space
- model free
- multi agent
- optimal policy
- markov decision processes
- state action space
- action selection
- control problems
- learning algorithm
- continuous state and action spaces
- multi agent reinforcement learning
- reinforcement learning methods
- machine learning
- temporal difference
- learning process
- dynamic programming
- continuous state
- stochastic approximation
- temporal difference learning
- eligibility traces
- optimal control
- learning problems
- function approximators
- partially observable
- policy search
- reward function
- learning agents
- transfer learning
- fixed point
- policy evaluation
- learning capabilities
- evaluation function