Counterexample Guided RL Policy Refinement Using Bayesian Optimization
Dec 6, 2021
Speakers
Briti Gangopadhyay
Speaker · 0 followers
Pallab Dasgupta
Speaker · 0 followers
About
Constructing Reinforcement Learning (RL) policies that adhere to safety requirements is an emerging field of study. RL agents learn via trial and error with an objective to optimize a reward signal. Often policies that are designed to accumulate rewards do not satisfy safety specifications. We present a methodology for counterexample guided refinement of a trained RL policy against a given safety specification. Our approach has two main components. The first component is an approach to discover failure trajectories using Bayesian optimization over multiple parameters of uncertainty from a policy learnt in a model-free setting. The second component selectively modifies the failure points of the policy using gradient-based updates. The approach has been tested on several RL environments, and we demonstrate that the policy can be made to respect the safety specifications through such targeted changes.Constructing Reinforcement Learning (RL) policies that adhere to safety requirements is an emerging field of study. RL agents learn via trial and error with an objective to optimize a reward signal. Often policies that are designed to accumulate rewards do not satisfy safety specifications. We present a methodology for counterexample guided refinement of a trained RL policy against a given safety specification. Our approach has two main components. The first component is an approach to discover…
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
Blending Anti-Aliasing into Vision Transformer
Watch later
Shengju Qian, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Principled Al Algorithms for predicting and mitigating climate change
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Understanding the Effect of Stochasticity in Policy Optimization
Watch later
Jincheng Mei, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Spotlight talks: new datasets and research finalists
Watch later
Sharmita Dey, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Knowledge-inspired 3D Scene Graph Prediction in Point Cloud
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Hyperparameter Tuning is All You Need for LISTA
Watch later
Xiaohan Chen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%