engblogs

Exploring how reinforcement learning agents learn bartering behavior and economic decision-making in a multi-agent environment.

The blogpost discusses how machine learning benchmarks in trading do not track what traders care about.

Exploring how populations of deep RL agents learn microeconomic behaviours, such as production, consumption, and trading of goods.

Applying a large-scale language model approach to build a single generalist agent capable of multi-modal, multi-task, multi-embodiment interactions.

Applying large-scale language modelling to build a multi-modal, multi-task, multi-embodiment generalist agent capable of playing games, captioning images, chatting, and performing physical tasks.

Active offline policy selection using offline data, special kernel, and Bayesian optimization for efficient RL policy evaluation

Using active offline policy selection (A-OPS) to improve the selection of RL policies for real-world applications by leveraging prerecorded datasets and limited interactions with the environment.

Exploring the latest developments in the OpenAI leadership team

Flamingo, a single visual language model, sets a new state of the art in few-shot learning on a wide range of multimodal tasks, outperforming fine-tuned and data-intensive methods.

When a passion for bass and brass help build better tools

The blogpost provides an overview of the new features and changes in Chrome 102 beta release, including the Window Controls Overlay for installed desktop web apps, finished origin trials, PWAs as file handlers, and more.

Exploring how Kevin Millikin's passion for bass and brass enriches his work as a software engineer on the DevTools team, showcased at PyCon US.