Enhanced Generalization Through Prioritization and Diversity in Self-Imitation Reinforcement Learning Over Procedural Environments with Sparse Rewards

Computer Science

• Reinforcement Learning 100%
• Art Performance 50%
• Proposed Modification 50%
• New-State 50%
• Singletons 50%
• Decision-Making 50%
• Feedback Signal 50%

Psychology

• Decision Making 100%
• Performance Art 100%

Social Sciences

• Imitation Learning 100%
• Learning Method 50%
• Decision Making 25%