Keyphrases
- cost efficient
- reinforcement learning
- dynamic environments
- optimal control
- dynamic programming
- changing environment
- real time
- execution environment
- learning algorithm
- decision making
- markov decision processes
- test bed
- machine learning
- multi agent environments
- initially unknown
- mobile robot
- multi agent
- learning agent
- control policy
- average reward
- temporal difference
- action selection
- risk neutral
- profit maximizing