Hindsight policy gradients

Keyphrases

• Reinforcement Learning Agent 100%
• Sparse Reward 100%
• Policy Gradient 100%
• Unseen 50%
• Sampling Efficiency 50%
• Policy Gradient Method 50%
• High-level Planning 50%
• Sample-efficient Learning 50%
• Subgoals 50%

Computer Science

• Learning Agent 100%
• Reinforcement Learning 100%
• Gradient Method 50%