Comparing Quadrotor Control Policies for Zero-Shot Reinforcement Learning under Uncertainty and Partial Observability.
Sven GronauerDaniel StümkeKlaus DiepoldPublished in: IROS (2023)
Keyphrases
- partial observability
- control policies
- reinforcement learning
- partially observable
- optimal policy
- action space
- control policy
- function approximation
- partially observable markov decision processes
- state space
- markov decision processes
- learning agent
- markov decision process
- reinforcement learning algorithms
- learning algorithm
- belief space
- model free
- belief state
- finite state
- multi agent
- planning problems
- random walk
- probabilistic model
- search algorithm
- optimal control
- orders of magnitude
- sufficient conditions
- np hard