Quantifying generalization in reinforcement learning
We’re releasing CoinRun, a training environment which provides a metric for an agent’s ability to transfer its experienc...
A centralized technology news hub bringing together the latest AI, software, cloud, cybersecurity, developer, and business technology news from trusted sources, updated automatically, all in one place.
We’re releasing CoinRun, a training environment which provides a metric for an agent’s ability to transfer its experienc...
We’re releasing Spinning Up in Deep RL, an educational resource designed to let anyone learn to become a skilled practit...
We’ve developed an energy-based model that can quickly learn to identify and generate instances of concepts, such as nea...
We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agen...
We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goal...
We are now accepting applications for our second cohort of OpenAI Scholars, a program where we provide 6–10 stipends and...
We are now accepting applications for OpenAI Fellows and Interns for 2019.
Our first cohort of OpenAI Scholars has now completed the program.
OpenAI Five lost two games against top Dota 2 players at The International in Vancouver this week, maintaining a good ch...
Everything you need to know about our aggregated technology radar.
A centralized technology news hub that aggregates the latest AI, software, cloud, cybersecurity, and business technology news from multiple trusted sources, organized into 7 categories.
New articles sync automatically roughly every 15 minutes, so the hub stays current without manual publishing.
25 curated RSS sources feed into the hub.
1,557 articles and counting, searchable and filterable by category and source.