InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations

By Yunzhu Li, Jiaming Song, Stefano Ermon. 2017

404 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Reinforcement Learning

Citations in the corpus

Imitating Interactive Intelligence (2020, methodology): “We are not aware of extant work that has applied GAIL to observations this high-dimensional (see Li et al. (2017); Zolna et al.”
A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, positive): “In the ﬁeld of navigation, Li et al. (2017) successfully apply GAIL in simulated autonomous vehicle navigation scenarios with raw visual input.”
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems (2019, methodology): “…imitation learning method, however standard GAIL does not work in the following settings: 1) POMDPs (Gangwani et al., 2019; ˙Zołna et al., 2019), 2) from pixels (Li et al., 2017; Reed et al., 2018), 3) off policy (Kostrikov et al., 2018) and 4) with variable initial conditions (Zolna et al., 2019).”
Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models (2017, background): “Empirically, GANs generate excellent samples of natural images (Radford, Metz, and Chintala 2015), audio signals (Pascual, Bonafonte, and Serrà 2017), and of behaviors in imitation learning (Ho and Ermon 2016; Li, Song, and Ermon 2017).”
Imitation Learning as f-Divergence Minimization (2019, methodology): “[4] show that a more sophisticated approach, GAIL [5], also exhibits a similar trend.”
Imitation Learning via Off-Policy Distribution Matching (2019, neutral): “Many of these applications of the AIL framework (Li et al., 2017; Hausman et al., 2017; Fu et al., 2017) maintain the same form of distribution ratio estimation as GAIL which necessitates on-policy samples.”
Bias and Generalization in Deep Generative Models: An Empirical Study (2018, background): “For example, it has been shown that on multiple natural image datasets, the learned distribution produces novel examples that generalize in meaningful ways, going beyond pixel space interpolation [15–17].”
Task-Relevant Adversarial Imitation Learning (2019, background): “Although many variants are introduced in the literature [Li et al., 2017, Fu et al., 2018, Merel et al., 2017, Zhu et al., 2018, Baram et al., 2017], making GAIL work for high-dimensional input spaces, particularly raw pixels, remains a challenge.”
Learning From Demonstration in the Wild (2018, methodology): “Related to ViBe are several existing LfD methods that learn road and pedestrian behaviour [29], [30], [31], [32].”
Positive-Unlabeled Reward Learning (2019, background): “Generative Adversarial Imitation Learning (GAIL; Ho & Ermon, 2016), has accrued a wide range of variants including Li et al. (2017), Fu et al. (2017), and Baram et al. (2017).”
Multi-task Maximum Entropy Inverse Reinforcement Learning (2018, methodology): “Recent extensions to GAIL augment trajectories with a latent intention variable that speciﬁes the task, and then maximise mutual information between the state-action pairs and intention variable (Hausman et al., 2017; Li et al., 2017).”
Universal Planning Networks (2018, background): “However, IRL from raw pixels is challenging due to the lack of sufficient constraints in the problem definition; only a couple of methods have successfully applied IRL to images, and to do so have relied on human domain knowledge (Wulfmeier et al., 2016) and pre-training (Li et al., 2017).”
InfoVAE: Balancing Learning and Inference in Variational Autoencoders (2019, background): “Generative models have shown great promise in modeling complex distributions such as natural images and text (Radford, Metz, and Chintala 2015; Zhu et al. 2017; Yang et al. 2017; Li, Song, and Ermon 2017).”
A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges (2023, positive): “in improved training stability, a technique that several AIL methods have implemented [77], [79].”