Effective Baselines for Multiple Object Rearrangement Planning in Partially Observable Mapped Environments.
Engin TekinElaheh BaratiNitin KamraRuta DesaiPublished in: CoRR (2023)
Keyphrases
- partially observable
- partial observability
- dynamical systems
- reinforcement learning
- decision problems
- markov decision processes
- state space
- planning domains
- infinite horizon
- belief state
- partially observable domains
- dynamic environments
- search space
- reward function
- ai planning
- belief space
- markov decision problems
- partially observable environments
- planning problems
- learning algorithm
- lower bound
- optimal solution
- fully observable