Imitation Beyond Expectation Using Pluralistic Stochastic Dominance
–Neural Information Processing Systems
Imitation learning seeks to estimate policies reflecting the values of demonstrated behaviors. Prevalent approaches learn to match or exceed the demonstrator's performance in expectation without knowing the demonstrator's reward function. Unfortunately, this does not induce pluralistic imitators that learn to support distinct demonstrations.
Neural Information Processing Systems
Jun-15-2026, 18:49:09 GMT
- Country:
- North America > United States (0.67)
- Genre:
- Research Report > Experimental Study (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Robots (1.00)
- Representation & Reasoning (1.00)
- Machine Learning
- Statistical Learning (1.00)
- Neural Networks (1.00)
- Reinforcement Learning (0.69)
- Information Technology > Artificial Intelligence