PROVABLE BENEFITS OF MULTI-TASK RL UNDER NON-MARKOVIAN DECISION MAKING PROCESSES

Computer Science

• Reinforcement Learning 100%
• Decision Making 100%
• Efficient Algorithm 50%
• Multitask Learning 50%
• Markov Decision Process 50%
• Latent Structure 50%
• Model Complexity 25%
• Single Individual 25%
• Sequential Decision Making 25%