Near-optimal regret bounds for stochastic shortest path

Keyphrases

• Agent Behavior 33%
• Environment Dynamics 33%
• Expected Cost 33%
• Goal State 33%
• Learning Algorithm 33%
• Minimum Cost 33%
• Near-optimal 100%
• Optimal Policy 33%
• Optimal Regret 100%
• Regret 33%
• Regret Bounds 100%
• Regret Minimization 33%
• Reinforcement Learning 33%
• Square Root 33%
• Stochastic Shortest Path 100%
• Total Expected Cost 33%
• Transition Function 33%

Computer Science

• Dynamic Environment 100%
• Learning Algorithm 100%
• Reinforcement Learning 100%
• Transition Function 100%

Mathematics

• Optimal Policy 50%
• Square Root 50%
• Stochastics 100%
• Transition Function 50%
• Upper Bound 50%
• Worst Case 50%