Multi-Fidelity Reinforcement Learning for Time-Optimal Quadrotor Re-planning.
Gilhyun RyouGeoffrey WangSertac KaramanPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- dynamic programming
- optimal control
- optimal plans
- action selection
- optimal planning
- multi agent
- worst case
- decision support
- learning algorithm
- optimal solution
- model free
- ai planning
- partially observable
- aerial vehicles
- deterministic domains
- partial observability
- blocks world
- initial state
- motion planning
- planning problems
- visual quality
- heuristic search
- mobile robot