Lights out: training RL agents robust to temporary blindness.
Nathan OrdonezMarije TrompPau Marquez JulbeWendelin BöhmerPublished in: CoRR (2023)
Keyphrases
- multi agent
- reinforcement learning
- multi agent systems
- learning agents
- cooperative
- multiagent systems
- software agents
- action selection
- dynamic environments
- intelligent agents
- neural network
- single agent
- multiple agents
- multiagent reinforcement learning
- complex environments
- training process
- autonomous agents
- training examples
- training set
- decision making
- learning capabilities
- state space
- multi agent reinforcement learning