MA-AC-MPC extends actor-critic MPC to multi-agent reinforcement learning and reports higher success rates than MLP baselines in pursuit-evasion simulation and hardware drone-rover landing.
Predictive Control with Learning-Based Terminal Costs Using Approximate Value Iteration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Merging model-based control with multi-agent reinforcement learning for multi-agent cooperative teaming strategies
MA-AC-MPC extends actor-critic MPC to multi-agent reinforcement learning and reports higher success rates than MLP baselines in pursuit-evasion simulation and hardware drone-rover landing.