The Next Input updates The Next Input-updates
Browse every published The Next Input update in a calm card overview with images, dates, and direct access to each article. Bekijk alle gepubliceerde The Next Input-updates in een rustig kaartenoverzicht met beelden, datums en directe toegang tot elk artikel.
The Next Input update The Next Input-update
Gym Retro Gym Retro
We’re releasing the full version of Gym Retro, a platform for reinforcement learning research on games. This brings our publicly-released game count from around 70 Atari games and 30 Sega games to over 1,000 games across a variety of backing emulators. We’re also releasing the tool we use to add new games to the platform. We’re releasing the full version of Gym Retro, a platform for reinforcement learning research on games. This brings our publicly-released game count from around 70 Atari games and 30 Sega games to over 1,000 games across a variety of backing emulators. We’re also releasing the tool we use to add new games to the platform.
The Next Input update The Next Input-update
AI and compute AI and compute
Title: AI and compute Title: AI and compute
The Next Input update The Next Input-update
AI safety via debate AI safety via debate
We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge who wins. We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge who wins.
The Next Input update The Next Input-update
Evolved Policy Gradients Evolved Policy Gradients
Title: Evolved Policy Gradients Title: Evolved Policy Gradients
The Next Input update The Next Input-update
Gotta Learn Fast: A new benchmark for generalization in RL Gotta Learn Fast: A new benchmark for generalization in RL
Read paper(opens in a new window) Read paper(opens in a new window)
The Next Input update The Next Input-update
Retro Contest Retro Contest
Title: Retro Contest Title: Retro Contest
The Next Input update The Next Input-update
Variance reduction for policy gradient with action-dependent factorized baselines Variance reduction for policy gradient with action-dependent factorized baselines
Read paper(opens in a new window) Read paper(opens in a new window)
The Next Input update The Next Input-update
Report from the OpenAI hackathon Report from the OpenAI hackathon
Title: Report from the OpenAI hackathon Title: Report from the OpenAI hackathon
The Next Input update The Next Input-update
Improving GANs using optimal transport Improving GANs using optimal transport
Read paper(opens in a new window) Read paper(opens in a new window)
The Next Input update The Next Input-update
On first-order meta-learning algorithms On first-order meta-learning algorithms
Read paper(opens in a new window) Read paper(opens in a new window)
The Next Input update The Next Input-update
Reptile: A scalable meta-learning algorithm Reptile: A scalable meta-learning algorithm
Read paper(opens in a new window)View code(opens in a new window) Read paper(opens in a new window)View code(opens in a new window)
The Next Input update The Next Input-update
OpenAI Scholars OpenAI Scholars
We’re providing 6–10 stipends and mentorship to individuals from underrepresented groups to study deep learning full-time for 3 months and open-source a project. We’re providing 6–10 stipends and mentorship to individuals from underrepresented groups to study deep learning full-time for 3 months and open-source a project.
Showing 877 to 888 of 993 updates. Je bekijkt 877 tot 888 van 993 updates.