Split Q Learning: Reinforcement Learning with Two-Stream Rewards.
Baihan LinDjallel BouneffoufGuillermo A. CecchiPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- data streams
- model free
- state space
- markov decision processes
- state action space
- control problems
- learning algorithm
- machine learning
- dynamic programming
- temporal difference
- sliding window
- multi agent
- optimal policy
- temporal difference learning
- reinforcement learning methods
- learning problems
- reward shaping
- eligibility traces
- optimal control
- continuous state and action spaces
- action selection
- continuous state
- function approximators
- policy iteration
- learning classifier systems