RL-TOPS: An Architecture for Modularity and Re-Use in Reinforcement Learning.
Malcolm R. K. RyanMark D. PendrithPublished in: ICML (1998)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- model free
- rl algorithms
- multi agent
- markov decision processes
- learning algorithm
- control problems
- temporal difference
- optimal policy
- continuous state
- machine learning
- actor critic
- state and action spaces
- action space
- direct policy search
- policy iteration
- learning capabilities
- learned knowledge
- action selection
- community detection
- learning problems
- reinforcement learning agents
- transfer learning
- dynamic programming