Learning Deep Decentralized Policy Network by Collective Rewards for Real-Time Combat Game.
Peixi PengJunliang XingLili CaoLisen MuChang HuangPublished in: IJCAI (2019)
Keyphrases
- real time
- learning algorithm
- learning process
- reinforcement learning
- role playing
- connectionist networks
- peer to peer
- cooperative
- wireless sensor networks
- recurrent networks
- deep architectures
- inverse reinforcement learning
- learning games
- deep learning
- partially observable
- serious games
- mobile learning
- supervised learning