Safe Policy Learning from Observations

Keyphrases

• Non-expert 100%
• Learning by Observation 100%
• Average Behavior 100%
• Policy Learning 100%
• Expert Data 100%
• Safety Policy 100%
• Crowdsourcing 50%
• Learning Environment 50%
• Behavioral Improvement 50%
• Search Process 50%
• Reinforcement Learning 50%
• Estimation Error 50%
• Behavioral Policy 50%
• Atari 50%
• Policy Gradient Method 50%
• Value Estimation 50%
• World Problems 50%
• Value Function 50%
• Policy Search 50%
• Grid World 50%
• Safe Learning 50%
• Safe Policy Improvement 50%
• Learning Methods 50%
• Expert Agent 50%
• Stochastic Policy 50%

Computer Science

• Average Behavior 100%
• Reinforcement Learning 50%
• Average Performance 50%
• Stochastic Policy 50%
• Function Value 50%
• Estimation Error 50%

Economics, Econometrics and Finance

• Crowdsourcing 100%
• Learning Environment 100%