Solving Continuous Control via Q-learning.
Tim SeydePeter WernerWilko SchwartingIgor GilitschenskiMartin A. RiedmillerDaniela RusMarkus WulfmeierPublished in: ICLR (2023)
Keyphrases
- control system
- state space
- control problems
- reinforcement learning
- control method
- learning algorithm
- optimal policy
- continuous state spaces
- action selection
- optimal control
- combinatorial optimization
- cooperative
- multi agent
- evolutionary algorithm
- control strategy
- artificial neural networks
- continuous domains
- genetic algorithm
- stochastic approximation
- potential field
- machine learning