Reinforcement Learning Based Approach For Urban Resource Allocation and Path Planning Problems.
Muhammad Fazalul RahmanNaveen SharmaPublished in: IDSTA (2020)
Keyphrases
- resource allocation
- planning problems
- reinforcement learning
- state space
- deterministic domains
- partial observability
- continuous state
- heuristic search
- domain independent
- resource management
- ai planning
- resource allocation problems
- fully observable
- planning systems
- function approximation
- markov decision processes
- optimal resource allocation
- reinforcement learning algorithms
- solving planning problems
- distributed resource allocation
- planning domains
- optimal policy
- stochastic domains
- learning algorithm
- path finding
- partially observable
- orders of magnitude
- combinatorial auctions
- partially observable markov decision processes
- machine learning
- dynamic programming
- resource allocation decisions
- allocation problems
- markov chain
- htn planning
- temporal difference
- binary decision diagrams
- belief state
- markov decision process
- shortest path
- reward function
- scarce resources
- general purpose
- classical planning
- resource allocation and scheduling