5.3k citations
- Google (United States)US2 papers
- Stanford UniversityUS2 papers
- Uber AI (United States)US2 papers
- University of California, BerkeleyUS2 papers
- University of Central FloridaUS2 papers
- Berkeley CollegeUS1 paper
- Bielefeld UniversityDE1 paper
- Carnegie Mellon UniversityUS1 paper
- Center for Security and Emerging TechnologyUS1 paper
- Center for Strategic and International StudiesUS1 paper
- Centre for the Governance of AI1 paper
- Columbia UniversityUS1 paper
12 papers · 1 filter
Exploration in Deep Reinforcement Learning: A Survey
Pawel Ladosz, Lilian Weng, Minwoo Kim +1
This paper reviews exploration techniques in deep reinforcement learning. Exploration techniques are of primary importance when solving sparse reward problems. In sparse reward pro…
Towards robust and domain agnostic reinforcement learning competitions
William Hebgen Guss, Stephanie Milani, Nicholay Topin +26
Reinforcement learning competitions have formed the basis for standard research benchmarks, galvanized advances in the state-of-the-art, and shaped the direction of the field. Desp…
Diffusion Models Beat GANs on Image Synthesis
Prafulla Dhariwal, Alex Nichol
We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models. We achieve this on unconditional image synthesis by findi…
Improved Denoising Diffusion Probabilistic Models
Alex Nichol, Prafulla Dhariwal
Denoising diffusion probabilistic models (DDPM) are a class of generative models which have recently been shown to produce excellent samples. We show that with a few simple modific…
Asymmetric self-play for automatic goal discovery in robotic manipulation
OpenAI OpenAI, Matthias Plappert, Raul Sampedro +13
We train a single, goal-conditioned policy that can solve many robotic manipulation tasks, including tasks with previously unseen goals and objects. We rely on asymmetric self-play…
Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
Rewon Child
We present a hierarchical VAE that, for the first time, generates samples quickly while outperforming the PixelCNN in log-likelihood on all natural image benchmarks. We begin by ob…