Internal reinforcement adaptive dynamic programming for optimal containment control of unknown continuous-time multi-agent systems.
Jiefu ZhangZhinan PengJiangping HuYiyi ZhaoRui LuoBijoy Kumar GhoshPublished in: Neurocomputing (2020)
Keyphrases
- dynamic programming
- optimal control
- multi agent systems
- reinforcement learning
- state space
- adaptive control
- infinite horizon
- control strategy
- exhaustive search
- control system
- piecewise linear
- markov chain
- optimal policy
- markov decision processes
- greedy algorithm
- mobile robot
- control method
- query evaluation
- game theory
- stereo matching
- control policy
- locally optimal
- special case
- internal and external
- distributed problem solving
- agent systems
- iterative learning control
- coarse to fine
- query optimization
- linear programming
- worst case
- data model
- multi agent