Cooperative Multi-agent Deep Reinforcement Learning in a 2 Versus 2 Free-Kick Task.
Jim Martin Catacora OcanaFrancesco RiccioRoberto CapobiancoDaniele NardiPublished in: RoboCup (2019)
Keyphrases
- reinforcement learning
- cooperative multi agent
- function approximation
- state space
- reinforcement learning algorithms
- learning algorithm
- control problems
- temporal difference learning
- multi agent
- reinforcement learning methods
- logic programming
- learning problems
- markov decision processes
- machine learning
- optimal control
- temporal difference
- transfer learning
- partially observable
- information retrieval
- multi agent reinforcement learning
- policy search
- robotic control
- decision trees
- function approximators
- model free
- supervised learning
- search space
- bayesian networks