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.
The Next Input update
Learning policy representations in multiagent systems
Read paper(opens in a new window)
The Next Input update
Improving language understanding with unsupervised learning
Read paper(opens in a new window)(opens in a new window)
The Next Input update
GamePad: A learning environment for theorem proving
Read paper(opens in a new window)
The Next Input update
OpenAI Fellows Fall 2018
We’re now accepting applications for the next cohort of OpenAI Fellows, a program which offers a compensated 6-month apprenticeship in AI research at OpenAI.
The Next Input update
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.
The Next Input update
AI and compute
Title: AI and compute
The Next Input update
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.
The Next Input update
Evolved Policy Gradients
Title: Evolved Policy Gradients
The Next Input update
Gotta Learn Fast: A new benchmark for generalization in RL
Read paper(opens in a new window)
The Next Input update
Retro Contest
Title: Retro Contest
The Next Input update
Variance reduction for policy gradient with action-dependent factorized baselines
Read paper(opens in a new window)
The Next Input update
Report from the OpenAI hackathon
Title: Report from the OpenAI hackathon
Showing 985 to 996 of 1,127 updates.