Using Collision Momentum in Deep Reinforcement Learning Based Adversarial Pedestrian Modeling.
Dianwei ChenEkim YurtseverKeith A. RedmillÜmit ÖzgünerPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- learning algorithm
- object detection
- collision detection
- learning classifier systems
- learning rate
- markov decision processes
- data sets
- dynamic programming
- learning process
- optimal policy
- multi agent systems
- decision trees
- pedestrian detection
- information systems
- information retrieval
- modeling method
- markov decision process
- collision avoidance
- machine learning