Time Limits in Reinforcement Learning.
Fabio PardoArash TavakoliVitaly LevdikPetar KormushevPublished in: ICML (2018)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- model free
- robotic control
- multi agent
- action selection
- state space
- markov decision processes
- policy search
- hidden markov models
- dynamic programming
- optimal policy
- data sets
- learning problems
- optimal control
- evolutionary algorithm
- search algorithm
- control problems
- stochastic approximation
- continuous state
- real world
- relational reinforcement learning
- databases