High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards.
Kai PloegerMichael LutterJan PetersPublished in: CoRL (2020)
Keyphrases
- reinforcement learning
- real world
- wide range
- markov decision processes
- state space
- function approximation
- data sets
- model free
- multi agent
- optimal policy
- hidden state
- reward function
- temporal difference
- synthetic data
- machine learning
- database
- case study
- learning classifier systems
- learning algorithm
- data mining
- reinforcement learning algorithms
- temporal difference learning
- reward shaping
- supervised learning
- synthetic datasets
- finite state
- multiple agents
- binary classifiers
- neural network