LSTM-based Abstraction of Hetero Observation and Transition in Non-Communicative Multi-Agent Reinforcement Learning.

Published in: ICAART (1) (2022)

Keyphrases

multi agent reinforcement learning
multi agent
learning agents
reinforcement learning
multi agent learning
recurrent neural networks
multi agent systems
associative memory
learning algorithm
domain knowledge
stochastic games
cooperative
state space
fuzzy logic
knowledge acquisition