Learning to Cooperate with Unseen Agent via Meta-Reinforcement Learning.
Rujikorn CharakornPoramate ManoonpongNat DilokthanakulPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- multi agent
- action selection
- learning agent
- learning agents
- learning problems
- learning tasks
- multiagent systems
- supervised learning
- state space
- decision theoretic
- previously unseen
- decision making
- reinforcement learning agents
- active exploration
- dynamic environments
- training examples
- neural network
- multi agent systems
- learning capabilities
- markov decision process
- learning environment
- state action
- temporal difference learning