The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions.
Mingyu KimJihwan OhYongsik LeeJoonkee KimSeonghwan KimSong ChongSe-Young YunPublished in: CoRR (2022)
Keyphrases
- multistage
- reinforcement learning
- multi agent
- environmental factors
- inverse reinforcement learning
- learning algorithm
- production system
- multiple agents
- stochastic programming
- optimal policy
- lot sizing
- learning agents
- active learning
- sufficient conditions
- stochastic optimization
- single stage
- higher order
- policy search