Towards Empathic Deep Q-Learning.
Bart BussmannJacqueline HeinermanJoel LehmanPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- cooperative
- function approximation
- multi agent
- state space
- learning algorithm
- stochastic approximation
- action selection
- learning rate
- temporal difference learning
- bucket brigade
- model free
- deep learning
- optimal policy
- cognitive tasks
- emotional state
- case study
- credit assignment
- belief nets
- potential field
- database
- dynamic programming
- support vector
- markov decision processes
- path planning
- multi agent systems