Learning Against Non-Stationary Agents with Opponent Modelling and Deep Reinforcement Learning.
Richard EverettStephen J. RobertsPublished in: AAAI Spring Symposia (2018)
Keyphrases
- non stationary
- reinforcement learning
- learning process
- learning agents
- multi agent
- multiagent learning
- action selection
- multi agent systems
- learning algorithm
- learned knowledge
- learning capabilities
- single agent
- state space
- learning agent
- white noise
- evolutionary learning
- function approximation
- learning tasks
- multiagent systems
- multiresolution