|
Some considerations on learning to explore via meta-reinforcement learning
|
OpenAI
|
2018-03-03 08:00
|
2026-02-28 05:56
|
—
|
|
Requests for Research 2.0
|
OpenAI
|
2018-01-31 08:00
|
2026-02-28 05:56
|
—
|
|
Ingredients for robotics research
|
OpenAI
|
2018-02-26 08:00
|
2026-02-28 05:56
|
—
|
|
OpenAI hackathon
|
OpenAI
|
2018-02-22 08:00
|
2026-02-28 05:56
|
—
|
|
OpenAI supporters
|
OpenAI
|
2018-02-20 08:00
|
2026-02-28 05:56
|
—
|
|
Discovering types for entity disambiguation
|
OpenAI
|
2018-02-07 08:00
|
2026-02-28 05:56
|
—
|
|
Scaling Kubernetes to 2,500 nodes
|
OpenAI
|
2018-01-18 08:00
|
2026-02-28 05:56
|
—
|
|
Learning sparse neural networks through L₀ regularization
|
OpenAI
|
2017-12-04 08:00
|
2026-02-28 05:56
|
—
|
|
Semi-supervised knowledge transfer for deep learning from private training data
|
OpenAI
|
2016-10-18 07:00
|
2026-02-28 05:56
|
—
|
|
Generalizing from simulation
|
OpenAI
|
2017-10-19 07:00
|
2026-02-28 05:56
|
—
|
|
Sim-to-real transfer of robotic control with dynamics randomization
|
OpenAI
|
2017-10-18 07:00
|
2026-02-28 05:56
|
—
|
|
Asymmetric actor critic for image-based robot learning
|
OpenAI
|
2017-10-18 07:00
|
2026-02-28 05:56
|
—
|
|
Domain randomization and generative models for robotic grasping
|
OpenAI
|
2017-10-17 07:00
|
2026-02-28 05:56
|
—
|
|
Meta-learning for wrestling
|
OpenAI
|
2017-10-11 07:00
|
2026-02-28 05:56
|
—
|
|
Nonlinear computation in deep linear networks
|
OpenAI
|
2017-09-29 07:00
|
2026-02-28 05:56
|
—
|
|
Dota 2
|
OpenAI
|
2017-08-11 07:00
|
2026-02-28 05:56
|
—
|
|
Gathering human feedback
|
OpenAI
|
2017-08-03 07:00
|
2026-02-28 05:56
|
—
|
|
Proximal Policy Optimization
|
OpenAI
|
2017-07-20 07:00
|
2026-02-28 05:56
|
—
|
|
Emergence of grounded compositional language in multi-agent populations
|
OpenAI
|
2017-03-15 07:00
|
2026-02-28 05:56
|
—
|
|
Robust adversarial inputs
|
OpenAI
|
2017-07-17 07:00
|
2026-02-28 05:56
|
—
|