A goal-conditioned policy search method with multi-timescale value function tuning

Computer Science

• Function Value 100%
• Reinforcement Learning 57%
• Robot 42%
• Generalization Performance 28%
• Optimization Policy 28%
• Selection Method 14%
• Experimental Result 14%
• Predictive Model 14%
• Motion Planning 14%
• Generalization Ability 14%
• And-States 14%
• Learning Skill 14%
• Integral Method 14%
• Networking Function 14%
• Model-Free Reinforcement Learning 14%
• Prediction Value 14%
• Soft Constraint 14%
• Constrained Environment 14%
• Policy Iteration 14%