Proceedings of the AAAI Conference on Artificial Intelligence · 2020 · 271 citations · 15 references
ComputingAutonomous SystemsComputer ScienceArtificial IntelligenceMachine LearningMarkov Decision ProcessesExploration-exploitation TradeoffMulti-agent SystemsPolicy LearningReinforcement LearningActor-network TheoryAlgorithmic ScalabilityDeep Reinforcement LearningReinforcement Learning In GamesScalability
We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games. This problem involves far more complicated state and action spaces than those of traditional 1v1 games, such as Go and Atari series, which makes it very difficult to search any policies with human-level performance. In this paper, we present a deep reinforcement learning framework to tackle this problem from the perspectives of both system and algorithm. Our system is of low coupling and high scalability, which enables efficient explorations at large scale. Our algorithm includes several novel strategies, including control dependency decoupling, action mask, target attention, and dual-clip PPO, with which our proposed actor-critic network can be effectively trained in our system. Tested on the MOBA game Honor of Kings, the trained AI agents can defeat top professional human players in full 1v1 games.
15
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Mastering the game of Go with deep neural networks and tree search
David Silver, Aja Huang, Chris J. Maddison et al. · Nature · 2016 · 15.8K citations
High-Dimensional Continuous Control Using Generalized Advantage Estimation
John Schulman, Philipp Moritz, Sergey Levine et al. · arXiv (Cornell University) · 2015 · 1.8K citations · Full text