Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition

2018-05-29 · NeurIPS 2018 12 · Justin Fu, Avi Singh, Dibya Ghosh, Larry Yang, Sergey Levine

The design of a reward function often poses a major practical challenge to real-world applications of reinforcement learning. Approaches such as inverse reinforcement learning attempt to overcome this challenge, but require expert demonstrations, which can be difficult or expensive to obtain in practice. We propose variational inverse control with events (VICE), which generalizes inverse reinforcement learning methods to cases where full demonstrations are not needed, such as when only samples of desired goal states are available. Our method is grounded in an alternative perspective on control and reinforcement learning, where an agent's goal is to maximize the probability that one or more events will happen at some point in the future, rather than maximizing cumulative rewards. We demonstrate the effectiveness of our methods on continuous control tasks, with a focus on high-dimensional observations like images where rewards are hard or even impossible to specify.

📄 PDF Abstract BibTeX arXiv:1805.11686

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-control Continuous Control reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Adversarial Imitation via Variational Inverse Reinforcement Learning

2018-09-17 · ICLR 2019 5 · Ahmed H. Qureshi, Byron Boots, Michael C. Yip

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regulariz…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Transfer Learning

Learning to Optimize via Wasserstein Deep Inverse Optimal Control

2018-05-22 · Yichen Wang, Le Song, Hongyuan Zha

We study the inverse optimal control problem in social sciences: we aim at learning a user's true cost function from the observed temporal behavior. In contrast to traditional phenomenological works that aim to learn a g…

Generative Adversarial Network Recommendation Systems Reinforcement Learning

Variational Regularization in Inverse Problems and Machine Learning

2021-12-08 · Martin Burger

This paper discusses basic results and recent developments on variational regularization methods, as developed for inverse problems. In a typical setup we review basic properties needed to obtain a convergent regularizat…

BIG-bench Machine Learning

Total Deep Variation: A Stable Regularizer for Inverse Problems

2020-06-15 · Erich Kobler, Alexander Effland, Karl Kunisch, Thomas Pock

Various problems in computer vision and medical imaging can be cast as inverse problems. A frequent method for solving inverse problems is the variational approach, which amounts to minimizing an energy composed of a dat…

Variational Mixture Models with Gamma or inverse-Gamma components

2016-07-26 · A. Llera, D. Vidaurre, R. H. R. Pruim, C. F. Beckmann

Mixture models with Gamma and or inverse-Gamma distributed mixture components are useful for medical image tissue segmentation or as post-hoc models for regression coefficients obtained from linear regression within a Ge…

blind source separation regression