LQR-Trees with Sampling Based Exploration of the State Space.
Jirí FejlekStefan RatschanPublished in: IROS (2023)
Keyphrases
- state space
- decision trees
- dynamical systems
- heuristic search
- reinforcement learning
- state variables
- dynamic programming
- motion planning
- optimal control
- monte carlo
- particle filter
- markov chain
- optimal policy
- reinforcement learning algorithms
- markov decision processes
- tree structure
- tree models
- planning problems
- search space
- action selection
- belief state
- action space
- tree construction
- markov decision problems
- continuous state spaces
- continuous time markov process
- linear quadratic
- stochastic domains
- tree mining
- initial state
- tree structures
- markov chain monte carlo
- genetic algorithm