Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards.
Yuhang SongJianyi WangThomas LukasiewiczZhenghua XuShangtong ZhangAndrzej WojcickiMai XuPublished in: AAAI (2020)
Keyphrases
- human level
- human level intelligence
- reinforcement learning
- machine intelligence
- artificial general intelligence
- bandit problems
- reward function
- intelligent systems
- web intelligence
- general intelligence
- artificial intelligence
- expected reward
- human level ai
- human intelligence
- cognitive science
- markov decision processes
- total reward
- ai systems
- discounted reward
- cognitive psychology
- cognitive architecture
- soft computing
- information processing
- knowledge base
- decision making