Active Task-Inference-Guided Deep Inverse Reinforcement Learning

Mathematics

• Reinforcement Learning 100%
• Reward 75%
• Markov Decision Process 27%
• Module 26%
• Query 21%
• Learning 20%
• Automata 9%
• State Space 9%
• Binary Response 6%
• Learning Algorithm 6%
• Maximum Entropy 6%
• Baseline 6%
• Iterative Process 6%
• Alternate 5%
• Encoding 5%
• Assign 5%
• Paradigm 5%
• Iterative Algorithm 5%
• History 4%
• Continue 4%
• Experiment 4%
• Iteration 3%
• Series 3%
• Performance 3%

Engineering & Materials Science

• Reinforcement learning 66%
• Markov processes 46%
• Entropy 9%
• Learning algorithms 9%
• Demonstrations 9%
• Feedback 7%
• Experiments 3%