Reinforcement Learning with Time-dependent Goals for Robotic Musicians.
Thilo FryenManfred EppePhuong D. H. NguyenTimo GerkmannStefan WermterPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- real robot
- function approximation
- perception action
- real time
- robotic control
- mobile robot
- state space
- learning algorithm
- multi agent
- reinforcement learning algorithms
- model free
- travel time
- robotic systems
- autonomous robots
- learning problems
- imitation learning
- machine learning
- temporal difference
- markov decision processes
- data mining
- stochastic approximation
- partial observability
- multi agent reinforcement learning
- policy search
- optimal policy
- dynamic programming