arXiv AI
Showing versus Doing: Teaching by Demonstration
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 18
Q-based Variational Inverse Reinforcement Learning
arXiv:2608. 16888v1 Announce Type: new Abstract: The development of safe and beneficial AI requires that systems can learn and act in accordance with human preferences.
arXiv Machine Learning
Jun 2
Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.
arXiv Machine Learning
Jul 8
Supervised Reward Inference
arXiv:2502. 18447v2 Announce Type: replace Abstract: Existing approaches to reward inference typically assume that humans provide demonstrations according to specific behavior models.
arXiv AI
Sep 10
DISEIL: Demonstration Distillation for Sample-Efficient Imitation Learning
arXiv:2609.08123v1 Announce Type: cross Abstract: A robot that can be taught a new task from a handful of demonstrations has to work out for itself what it still cannot do, and then ask for exactly t...
arXiv Machine Learning
3d ago
Inverse RL Helps Align AI by Imitating Humans
The paper introduces PARED, an approach that uses inverse reinforcement learning to derive an explicit, interpretable reward from expert demonstrations. By training a lightweight discriminator on response-level features, PARED can guide both inference-time reranking and on-policy reinforcement learning, improving alignment for models that have not undergone supervised fine-tuning and further refining those that have. The method also supports contextual alignment, enabling a single policy to adapt its responses to different audience preferences.
arXiv Machine Learning
Jun 4
Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning
arXiv:2603. 09803v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance.