Wed Oct 05 2022
Mon Oct 03 2022

Scaling Laws for a Multi-Agent Reinforcement Learning Model

Deep Learning
Artificial Intelligence
Reinforcement Learning
Reinforcement learning in game-playing

Study of performance scaling for AlphaZero agents in Connect Four and Pentago games. Finds similar scaling exponents to language models and underparametrization of SotA game-playing models for available compute.

Suggests optimal neural network size for improved performance in reinforcement learning models, and highlights the underutilization of available compute in SotA game-playing models.

Calibrating Sequence likelihood Improves Conditional Language Generation

Deep Learning
Natural Language Processing
Artificial Intelligence
Language generation tasks

Introduces sequence likelihood calibration (SLiC) to align model-generated sequence likelihood to reference sequences, improving decoding candidates' quality without reduction in performance with model scale.

Shows that SLiC exceeds or matches SotA results in generation tasks and presents a way to improve quality with limited training and inference budgets.

Improving Sample Quality of Diffusion Model Using Self-Attention Guidance

Deep Learning
Computer Vision
Artificial Intelligence
Image generation in diffusion models

Introduces label-free guidance through self-attention maps for enhancing quality of generated images in diffusion models.

Suggests SAG as a strategy to improve quality of generated images and shows its efficacy in various diffusion models.

Fri Sep 30 2022
Sun Sep 25 2022
Thu Sep 22 2022
Sun Sep 18 2022