The Surprising Effectiveness of MAPPO in Cooperative, Multi-Agent Games

208 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations (2021, positive): “In this experiment, we use QMIX (Rashid et al., 2018), MADDPG (Lowe et al., 2017), CDS (Li et al., 2021) and MAPPO (Yu et al., 2021) as the baselines.”
Multi-Agent Reinforcement Learning is a Sequence Modeling Problem (2022, methodology): “MAPPO [46] is the ﬁrst, and the most direct, approach for applying PPO in MARL.”
A Review of Deep Reinforcement Learning for Smart Building Energy Management (2020, unknown): “DQN Value-based, off-policy, single-agent [28] Double DQN Value-based, off-policy, single-agent [72] Dueling DQN Value-based, off-policy, single-agent [73] Prioritized DQN Value-based, off-policy, single-agent [74] Distributional DQN Value-based, off-policy, single-agent [75] Noisy DQN Value-based, ”
Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning (2021, methodology): “We consider two most common (Yu et al., 2021) are known to achieve supreme results on this benchmark.”
Dealing with Non-Stationarity in MARL via Trust-Region Decomposition (2021, methodology): “Yu et al. (2021) proposed MAPPO which enhances IPPO by considering a joint critic function and ﬁner implementation techniques for on-policy methods.”