Unknown mixing times in apprenticeship and reinforcement learning

Keyphrases

• Reinforcement Learning 100%
• Mixing Time 100%
• Apprenticeship Learning 100%
• Learning Algorithm 50%
• Policy Evaluation 50%
• Existing Algorithms 50%
• Sample Complexity 50%
• Sampling Algorithm 50%
• Policy Gradient 50%
• Average Reward Criterion 50%
• Learning Policy 50%
• Markov Chain Theory 50%

Computer Science

• Learning Algorithm 100%
• Markov Chain 100%
• Sampling Algorithm 100%
• Reinforcement Learning 100%
• Apprenticeship Learning 100%