Suppressing Overestimation in Q-Learning through Adversarial Behaviors.
HyeAnn LeeDonghwan LeePublished in: CoRR (2023)
Keyphrases
- multi agent
- reinforcement learning
- cooperative
- function approximation
- learning algorithm
- state space
- real robot
- bucket brigade
- multi agent reinforcement learning
- learning rate
- stochastic approximation
- behavior analysis
- optimal policy
- neural network
- model free
- single agent
- markov decision processes
- path planning
- behavior patterns
- state action
- behavior recognition
- potential field
- least squares
- mobile robot
- credit assignment