paper-with-me

Papers

Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning

2018-09-09 · ICLR 2019 5 · Ilya Kostrikov, Kumar Krishna Agrawal, Debidatta Dwibedi, Sergey Levine, Jonathan Tompson

We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used in these algorithms. While these biases might work well for some environments, they can also lead to sub-optimal behavior in others. Secondly, even though these algorithms can learn from few expert demonstrations, they require a prohibitively large number of interactions with the environment in order to imitate the expert for many real-world applications. In order to address these issues, we propose a new algorithm called Discriminator-Actor-Critic that uses off-policy Reinforcement Learning to reduce policy-environment interaction sample complexity by an average factor of 10. Furthermore, since our reward function is designed to be unbiased, we can apply our algorithm to many problems without making any task-specific adjustments.

📄 PDF Abstract BibTeX arXiv:1809.02925

Code (3)

Kaixhin/imitation-learning pytorch
illidanlab/opolo-code
illidanlab/sail tf

Tasks

Imitation LearningReinforcement Learning

Similar Papers 제목 키워드 기반

SAC-NeRF: Adaptive Ray Sampling for Neural Radiance Fields via Soft Actor-Critic Reinforcement Learning

2025-12-31 · Chenyu Ge arxiv

Neural Radiance Fields (NeRF) have achieved photorealistic novel view synthesis but suffer from computational inefficiency due to dense ray sampling during volume rendering. We propose SAC-NeRF, a reinforcement learning …

Reinforcement LearningNovel View Synthesis

Is Discriminator a Good Feature Extractor?

2019-12-02 · Xin Mao, Zhaoyu Su, Pin Siang Tan, Jun Kang Chow 외

The discriminator from generative adversarial nets (GAN) has been used by researchers as a feature extractor in transfer learning and appeared worked well. However, there are also studies that believe this is the wrong r…

Transfer Learning

PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learning

2019-10-31 · Iou-Jen Liu, Raymond A. Yeh, Alexander G. Schwing

Sample efficiency and scalability to a large number of agents are two important goals for multi-agent reinforcement learning systems. Recent works got us closer to those goals, addressing non-stationarity of the environm…

Deep Reinforcement LearningMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+1

Adversarial Bootstrapping for Dialogue Model Training

2019-09-03 · Oluwatobi Olabiyi, Erik T. Mueller, Christopher Larson, Tarek Lahlou

Open domain neural dialogue models, despite their successes, are known to produce responses that lack relevance, diversity, and in many cases coherence. These shortcomings stem from the limited ability of common training…

Diversitymodel

Adversarially Guided Actor-Critic

2021-02-08 · ICLR 2021 1 · Yannis Flet-Berliac, Johan Ferret, Olivier Pietquin, Philippe Preux 외

Despite definite success in deep reinforcement learning problems, actor-critic algorithms are still confronted with sample inefficiency in complex environments, particularly in tasks where efficient exploration is a bott…

Deep Reinforcement LearningEfficient Exploration