Improving Generative Adversarial Imitation Learning with Non-expert Demonstrations

2018-09-27 · Voot Tangkaratt, Masashi Sugiyama

Imitation learning aims to learn an optimal policy from expert demonstrations and its recent combination with deep learning has shown impressive performance. However, collecting a large number of expert demonstrations for deep learning is time-consuming and requires much expert effort. In this paper, we propose a method to improve generative adversarial imitation learning by using additional information from non-expert demonstrations which are easier to obtain. The key idea of our method is to perform multiclass classification to learn discriminator functions where non-expert demonstrations are regarded as being drawn from an extra class. Experiments in continuous control tasks demonstrate that our method learns better policies than the generative adversarial imitation learning baseline when the number of expert demonstrations is small.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-control Continuous ControlDeep LearningImitation Learning

Hindsight Generative Adversarial Imitation Learning

2019-03-19 · Naijun Liu, Tao Lu, Yinghao Cai, Boyao Li 외

Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration dat…

Imitation Learning Reinforcement Learning Reinforcement Learning (RL)

f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learning

2020-12-01 · NeurIPS 2020 12 · Xin Zhang, Yanhua Li, Ziming Zhang, Zhi-Li Zhang

Imitation learning (IL) aims to learn a policy from expert demonstrations that minimizes the discrepancy between the learner and expert behaviors. Various imitation learning algorithms have been proposed with different p…

Imitation Learning

$f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning

2020-10-02 · Xin Zhang, Yanhua Li, Ziming Zhang, Zhi-Li Zhang

Imitation Learning

Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance

2024-01-21 · Zheng Fang, Tianhao Chen, Dong Jiang, Zheng Zhang 외

Multiple autonomous underwater vehicles (multi-AUV) can cooperatively accomplish tasks that a single AUV cannot complete. Recently, multi-agent reinforcement learning has been introduced to control of multi-AUV. However,…

Imitation Learning Multi-agent Reinforcement Learning

Learning from Demonstrations with Energy based Generative Adversarial Imitation Learning

2021-01-01 · Kaifeng Zhang

Traditional reinforcement learning methods usually deal with the tasks with explicit reward signals. However, for vast majority of cases, the environment wouldn't feedback a reward signal immediately. It turns out to be …

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