Hindsight Intermediate Targets for Mapless Navigation With Deep Reinforcement Learning.
Yoonsu JangJongchan BaekSoohee HanPublished in: IEEE Trans. Ind. Electron. (2022)
Keyphrases
- reinforcement learning
- action selection
- function approximation
- blind and visually impaired
- learning algorithm
- dynamic programming
- markov decision processes
- machine learning
- reinforcement learning algorithms
- model free
- moving target
- state space
- multi agent reinforcement learning
- robot navigation
- temporal difference
- autonomous navigation
- temporal difference learning
- multi agent systems
- data sets
- robotic control
- stochastic approximation
- navigation systems
- target recognition
- learning problems
- optimal policy
- optimal control
- monte carlo