Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control

Keyphrases

• Hierarchical Imitation Learning 100%
• Expert Demonstration 50%
• Hierarchical Policy 50%
• Task Hierarchy 50%
• Long-horizon Tasks 50%
• Directed Information 50%

Computer Science

• Reinforcement Learning 100%
• Autoencoder 50%
• Learning Algorithm 50%
• Objective Function 50%
• Causal Relationship 50%