paper-with-me

Papers

Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency

2021-12-11 · Mingfei Sun, Sam Devlin, Katja Hofmann, Shimon Whiteson

Sample efficiency is crucial for imitation learning methods to be applicable in real-world applications. Many studies improve sample efficiency by extending adversarial imitation to be off-policy regardless of the fact that these off-policy extensions could either change the original objective or involve complicated optimization. We revisit the foundation of adversarial imitation and propose an off-policy sample efficient approach that requires no adversarial training or min-max optimization. Our formulation capitalizes on two key insights: (1) the similarity between the Bellman equation and the stationary state-action distribution equation allows us to derive a novel temporal difference (TD) learning approach; and (2) the use of a deterministic policy simplifies the TD learning. Combined, these insights yield a practical algorithm, Deterministic and Discriminative Imitation (D2-Imitation), which operates by first partitioning samples into two replay buffers and then learning a deterministic policy via off-policy reinforcement learning. Our empirical results show that D2-Imitation is effective in achieving good sample efficiency, outperforming several off-policy extension approaches of adversarial imitation on many control tasks.

📄 PDF Abstract BibTeX arXiv:2112.06054

Code (1)

mingfeisun/d2-imitation 공식 구현 tf

Tasks

Imitation Learning

Similar Papers 제목 키워드 기반

Imitation Learning by Reinforcement Learning

2021-08-10 · ICLR 2022 4 · Kamil Ciosek

Imitation learning algorithms learn a policy from demonstrations of expert behavior. We show that, for deterministic experts, imitation learning can be done by reduction to reinforcement learning with a stationary reward…

continuous-controlContinuous ControlImitation Learningreinforcement-learning+2

Adversarial training for predictive tasks: theoretical analysis and limitations in the deterministic case

2020-11-02 · Thibault Lesieur, Jérémie Messud, Issa Hammoud, Hanyuan Peng 외

To train a deep neural network to mimic the outcomes of processing sequences, a version of Conditional Generalized Adversarial Network (CGAN) can be used. It has been observed by others that CGAN can help to improve the …

Adversarial training for predictive tasks: theoretical analysis and limitations in the deterministic case.

2020-10-19 · NeurIPS Workshop ICBINB 2020 12 · Thibault Lesieur, Jérémie Messud, Issa Hammoud, Hanyuan Peng 외

To train a deep neural network to mimic the outcomes of processing sequences, a version of Conditional Generalized Adversarial Network (CGAN) can be used. It has been observed by others that CGAN can help to improve the …

Semi-Supervised Adversarial Discriminative Domain Adaptation

2021-09-27 · Thai-Vu Nguyen, Anh Nguyen, Nghia Le, Bac Le

Domain adaptation is a potential method to train a powerful deep neural network, which can handle the absence of labeled data. More precisely, domain adaptation solving the limitation called dataset bias or domain shift …

Domain AdaptationEmotion Recognition

Deterministic Policy Imitation Gradient Algorithm

2018-01-01 · ICLR 2018 1 · Fumihiro Sasaki, Atsuo Kawaguchi

The goal of imitation learning (IL) is to enable a learner to imitate an expert’s behavior given the expert’s demonstrations. Recently, generative adversarial imitation learning (GAIL) has successfully achieved it even o…

continuous-controlContinuous ControlImitation Learning