Addressing Myopic Constrained POMDP Planning with Recursive Dual Ascent.
Paula StoccoSuhas ChundiArec L. JamgochianMykel J. KochenderferPublished in: CoRR (2024)
Keyphrases
- planning problems
- belief space
- partially observable markov decision processes
- partially observable
- partially observable markov decision process
- belief state
- reinforcement learning
- stochastic domains
- partially observable stochastic domains
- ai planning
- state space
- finite state
- predictive state representations
- infinite horizon
- planning under uncertainty
- plan generation
- motion planning
- heuristic search
- dynamical systems
- decision theoretic
- domain independent
- planning process
- partial observability
- multi agent
- blocks world
- decision problems
- reward function
- continuous state
- learning algorithm
- machine learning