×
Dec 19, 2019 · We propose an event-based policy gradient to train the leader and an action abstraction policy gradient to train the followers in leader-follower Markov game.
In this paper, we solve the large-scale sequential expensive coordination problem with a novel RL training scheme. There are several lines of works related to ...
Existing works in deep Multi-Agent Reinforcement Learning (MARL) mainly focus on coordinating cooperative agents to complete certain tasks jointly.
Papertalk is an open-source platform where scientists share video presentations about their newest scientific results - and watch, like + discuss them.
Learning expensive coordination: An event-based deep RL approach. R Yu, Z Shi, X Wang, R Wang, Y Zhang, H Lai, B An. International Conference on Learning ...
Learning Expensive Coordination: An Event-Based Deep RL Approach · no code implementations • ICLR 2020 • Zhenyu Shi*, Runsheng Yu*, Xinrun Wang*, Rundong Wang ...
RMIX: Learning risk-sensitive policies for cooperative reinforcement learning agents ... Learning expensive coordination: An event-based deep RL approach. R Yu, X ...
People also ask
Learning Expensive Coordination: An Event-Based Deep RL Approach. Zhenyu Shi ... VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning.
This study integrates supervisory control theory and a model-based deep reinforcement learning method to synthesize a nonblocking coordinator for the modular ...
Missing: Expensive | Show results with:Expensive
Learning Expensive Coordination: An Event-Based Deep RL Approach · no code ... Inducing Cooperation via Team Regret Minimization based Multi-Agent Deep ...