English
Related papers

Related papers: A GAN-Like Approach for Physics-Based Imitation Le…

200 papers

This paper considers learning robot locomotion and manipulation tasks from expert demonstrations. Generative adversarial imitation learning (GAIL) trains a discriminator that distinguishes expert from agent transitions, and in turn use a…

Machine Learning · Computer Science 2022-06-24 Tianyu Wang , Nikhil Karnwal , Nikolay Atanasov

This paper introduces a new imitation learning framework based on energy-based generative models capable of learning complex, physics-dependent, robot motion policies through state-only expert motion trajectories. Our algorithm, called…

Robotics · Computer Science 2025-02-13 Anish Abhijit Diwan , Julen Urain , Jens Kober , Jan Peters

This paper describes an approach that combines generative adversarial networks (GANs) with interactive evolutionary computation (IEC). While GANs can be trained to produce lifelike images, they are normally sampled randomly from the learned…

Neural and Evolutionary Computing · Computer Science 2018-01-26 Philip Bontrager , Wending Lin , Julian Togelius , Sebastian Risi

Deep reinforcement learning (DRL) has achieved great successes in many simulated tasks. The sample inefficiency problem makes applying traditional DRL methods to real-world robots a great challenge. Generative Adversarial Imitation Learning…

Machine Learning · Computer Science 2021-04-15 Jie Huang , Rongshun Juan , Randy Gomez , Keisuke Nakamura , Qixin Sha , Bo He , Guangliang Li

Generative Adversarial Networks (GANs) have gained momentum for their ability to model image distributions. They learn to emulate the training set and that enables sampling from that domain and using the knowledge learned for useful…

Computer Vision and Pattern Recognition · Computer Science 2019-04-18 Abdullah Hamdi , Bernard Ghanem

In many sequential decision-making problems (e.g., robotics control, game playing, sequential prediction), human or expert data is available containing useful information about the task. However, imitation learning (IL) from a small amount…

Machine Learning · Computer Science 2022-11-04 Divyansh Garg , Shuvam Chakraborty , Chris Cundy , Jiaming Song , Matthieu Geist , Stefano Ermon

The success of deep reinforcement learning (RL) and imitation learning (IL) in vision-based robotic manipulation typically hinges on the expense of large scale data collection. With simulation, data to train a policy can be collected…

Robotics · Computer Science 2021-07-06 Daniel Ho , Kanishka Rao , Zhuo Xu , Eric Jang , Mohi Khansari , Yunfei Bai

The existing Motion Imitation models typically require expert data obtained through MoCap devices, but the vast amount of training data needed is difficult to acquire, necessitating substantial investments of financial resources, manpower,…

Robotics · Computer Science 2024-05-03 Liu Qiyuan

A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language. Here we study how to design artificial…

Training a high-dimensional simulated agent with an under-specified reward function often leads the agent to learn physically infeasible strategies that are ineffective when deployed in the real world. To mitigate these unnatural behaviors,…

Artificial Intelligence · Computer Science 2022-03-30 Alejandro Escontrela , Xue Bin Peng , Wenhao Yu , Tingnan Zhang , Atil Iscen , Ken Goldberg , Pieter Abbeel

In this paper, we introduce ControlVAE, a novel model-based framework for learning generative motion control policies based on variational autoencoders (VAE). Our framework can learn a rich and flexible latent representation of skills and a…

Graphics · Computer Science 2022-10-13 Heyuan Yao , Zhenhua Song , Baoquan Chen , Libin Liu

GANs provide a framework for training generative models which mimic a data distribution. However, in many cases we wish to train these generative models to optimize some auxiliary objective function within the data it generates, such as…

Computer Vision and Pattern Recognition · Computer Science 2017-10-02 Andrew Kyle Lampinen , David So , Douglas Eck , Fred Bertsch

Prediction of human actions in social interactions has important applications in the design of social robots or artificial avatars. In this paper, we focus on a unimodal representation of interactions and propose to tackle interaction…

Neural and Evolutionary Computing · Computer Science 2022-09-13 Louis Airale , Dominique Vaufreydaz , Xavier Alameda-Pineda

GANs have two competing modules: the generator module is trained to generate new examples, and the discriminator module is trained to discriminate real examples from generated examples. The training procedure of GAN is modeled as a finitely…

Machine Learning · Computer Science 2022-09-29 Ch. Sobhan Babu , Ravindra Guravannavar , Arvind Hulgeri

Motivated by humans' ability to adapt skills in the learning of new ones, this paper presents AdaptNet, an approach for modifying the latent space of existing policies to allow new behaviors to be quickly learned from like tasks in…

Many modern methods for imitation learning and inverse reinforcement learning, such as GAIL or AIRL, are based on an adversarial formulation. These methods apply GANs to match the expert's distribution over states and actions with the…

Machine Learning · Computer Science 2020-08-11 Oleg Arenz , Gerhard Neumann

Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their…

Generative adversarial network (GAN) has gotten wide re-search interest in the field of deep learning. Variations of GAN have achieved competitive results on specific tasks. However, the stability of training and diversity of generated…

Computer Vision and Pattern Recognition · Computer Science 2018-09-07 Haoxuan You , Zhicheng Jiao , Haojun Xu , Jie Li , Ying Wang , Xinbo Gao

Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising approach towards…

Adversarial Imitation Learning alternates between learning a discriminator -- which tells apart expert's demonstrations from generated ones -- and a generator's policy to produce trajectories that can fool this discriminator. This…

Machine Learning · Computer Science 2021-04-19 Paul Barde , Julien Roy , Wonseok Jeon , Joelle Pineau , Christopher Pal , Derek Nowrouzezahrai