Policy Learning Using Weak Supervision
Dec 6, 2021
Speakers
Jingkang Wang
Speaker · 0 followers
Hongyi Guo
Speaker · 0 followers
Zhaowei Zhu
Speaker · 0 followers
About
Most existing policy learning solutions require the learning agents to receive high-quality supervision signals, e.g., rewards in reinforcement learning (RL) or high-quality expert demonstrations in behavioral cloning (BC). These quality supervisions are either infeasible or prohibitively expensive to obtain in practice. We aim for a unified framework that leverages the available cheap weak supervisions to perform policy learning efficiently. To handle this problem, we treat the weak supervision” as imperfect information coming from a peer agent, and evaluate the learning agent's policy based on a correlated agreement” with the peer agent's policy (instead of simple agreements). Our approach explicitly punishes a policy for overfitting to the weak supervision. In addition to theoretical guarantees, extensive evaluations on tasks including RL with noisy reward, BC with weak demonstrations, and standard policy co-training (RL + BC) show that our method leads to substantial performance improvements, especially when the complexity or the noise of the learning environments is high.Most existing policy learning solutions require the learning agents to receive high-quality supervision signals, e.g., rewards in reinforcement learning (RL) or high-quality expert demonstrations in behavioral cloning (BC). These quality supervisions are either infeasible or prohibitively expensive to obtain in practice. We aim for a unified framework that leverages the available cheap weak supervisions to perform policy learning efficiently. To handle this problem, we treat the weak supervision…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods
Watch later
Terrance Liu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Deep Residual Learning in Spiking Neural Networks
Watch later
Wei Fang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Activation Sharing with Asymmetric Paths Solves Weight Transport Problem without Bidirectional Connection
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Benign Overfitting
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
The Banality of Scale: A Theory on the Limits of Modeling Bias and Fairness Frameworks for Social Justice (and other lessons from the Pandemic)
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Why We Want Contrastive Learning in Language Models
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%