EnCoMP: Enhanced Covert Maneuver Planning using Offline Reinforcement Learning.
Jumman HossainAbu Zaher Md FarideeNirmalya RoyPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- action selection
- real time
- deterministic domains
- planning problems
- macro actions
- partially observable
- information flow
- state space
- multi agent
- stochastic domains
- markov decision processes
- mobile robot
- function approximation
- planning process
- model free
- plan generation
- robotic control
- complex domains
- partially observable domains
- closed loop
- heuristic search
- optimal policy
- learning algorithm
- reinforcement learning algorithms
- path finding
- temporal difference
- partially observable markov decision processes
- plan execution
- mixed initiative
- motion planning
- blocks world
- partial observability
- social networks
- machine learning