An effective maximum entropy exploration approach for deceptive game in reinforcement learning.
Chunmao LiXuanguang WeiYinliang ZhaoXupeng GengPublished in: Neurocomputing (2020)
Keyphrases
- maximum entropy
- reinforcement learning
- maximum entropy principle
- transformation based learning
- maximum entropy model
- markov models
- principle of maximum entropy
- random fields
- optimal policy
- probabilistic logic
- minimum cross entropy
- conditional random fields
- multi class
- active exploration
- iterative scaling
- learning process
- learning algorithm
- action selection
- state space
- hidden markov models