Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality

Keyphrases

• Learning Performance 100%
• Stochastic Shortest Path Problem 100%
• Path Learning 100%
• Stochastic Shortest Path 100%
• Evaluation Policy 50%
• Reinforcement Learning 50%
• State Space 50%
• SIMPLE Algorithm 50%
• Real-world Application 50%
• Learning Task 50%
• Online Environment 50%
• Goal-oriented 50%
• Minimax Optimal 50%
• Worst-case Bounds 50%
• Historical Data 50%
• Online Interaction 50%
• Statistical Limit 50%
• Action Space 50%
• Theoretical Formulation 50%
• Off-policy Evaluation 50%
• Goal State 50%
• Offline Policy Learning 50%

Computer Science

• Shortest Path Problem 100%
• State Space 50%
• Simple Algorithm 50%
• World Application 50%
• Reinforcement Learning 50%
• Historical Data 50%
• Theoretical Formulation 50%