Deep Reinforcement Learning for Pedestrian Guidance.
Hitoshi ShimizuTakanori HaraTomoharu IwataPublished in: PRIMA (2020)
Keyphrases
- reinforcement learning
- pedestrian detection
- state space
- function approximation
- object detection
- robotic control
- reinforcement learning algorithms
- markov decision processes
- model free
- multi agent
- temporal difference learning
- temporal difference
- optimal policy
- stochastic approximation
- control problems
- learning agents
- function approximators
- learning capabilities
- information retrieval
- belief nets
- reinforcement learning methods
- learning agent
- deep learning
- action selection
- learning process
- probabilistic model
- transfer learning
- human body