A Deep Bayesian Policy Reuse Approach Against Non-Stationary Agents.
Yan ZhengZhaopeng MengJianye HaoZongzhang ZhangTianpei YangChangjie FanPublished in: NeurIPS (2018)
Keyphrases
- non stationary
- multi agent systems
- multi agent
- action selection
- multiagent systems
- belief nets
- intelligent agents
- autoregressive
- multiple agents
- software agents
- agent receives
- cooperative
- autonomous agents
- random fields
- adaptive algorithms
- learning objects
- bayesian networks
- data mining
- temporal evolution
- empirical mode decomposition
- optimal policy
- markov decision process
- finite horizon
- multi component