Spatially and Seamlessly Hierarchical Reinforcement Learning for State Space and Policy space in Autonomous Driving.
Jaehyun KimJaeseung JeongPublished in: CoRR (2021)
Keyphrases
- state space
- hierarchical reinforcement learning
- autonomous driving
- markov decision process
- action space
- optimal policy
- reward function
- state abstraction
- reinforcement learning
- search space
- average reward
- markov decision processes
- markov decision problems
- grand challenge
- heuristic search
- markov chain
- dynamical systems
- infinite horizon
- multiple agents
- dynamic programming
- computer vision
- mobile robot
- policy iteration
- linear programming
- initial state
- partially observable
- stereo vision