History-based single Belief State Generation for Partially Observable Real-Time Strategy Games.
Weilong YangYong PengQuanjun YinLin SunPublished in: WSC (2018)
Keyphrases
- partially observable
- belief state
- real time strategy games
- state space
- partial observability
- belief revision
- belief space
- decision problems
- reinforcement learning
- dynamical systems
- markov decision processes
- partially observable markov decision processes
- markov decision problems
- partially observable markov decision process
- case based planning
- reward function
- special case
- imperfect information
- dynamic systems
- markov chain