Archive - DiekNews

Requests for Research 2.0

Scaling Kubernetes to 2,500 nodes

Block-sparse GPU kernels

Learning sparse neural networks through L₀ regularization

Interpretable and pedagogical examples

Learning a hierarchy

Generalizing from simulation

Sim-to-real transfer of robotic control with dynamics randomization

Asymmetric actor critic for image-based robot learning

Domain randomization and generative models for robotic grasping

Latest

Requests for Research 2.0

8 years ago 56

Scaling Kubernetes to 2,500 nodes

8 years ago 61

Block-sparse GPU kernels

8 years ago 77

Learning sparse neural networks through L₀ regular...

8 years ago 59

Interpretable and pedagogical examples

9 years ago 63

Learning a hierarchy

9 years ago 55

Generalizing from simulation

9 years ago 57

Sim-to-real transfer of robotic control with dynam...

9 years ago 56

Asymmetric actor critic for image-based robot lear...

9 years ago 57

Domain randomization and generative models for rob...

9 years ago 57

Meta-learning for wrestling

9 years ago 56

Competitive self-play

9 years ago 53

Nonlinear computation in deep linear networks

9 years ago 54

Learning to model other minds

9 years ago 69

Learning with opponent-learning awareness

9 years ago 58

OpenAI Baselines: ACKTR & A2C

9 years ago 69

More on Dota 2

9 years ago 54

Dota 2

9 years ago 58

Requests for Research 2.0

Scaling Kubernetes to 2,500 nodes

Block-sparse GPU kernels

Learning sparse neural networks through L₀ regularization

Interpretable and pedagogical examples

Learning a hierarchy

Generalizing from simulation

Sim-to-real transfer of robotic control with dynamics randomization

Asymmetric actor critic for image-based robot learning

Domain randomization and generative models for robotic grasping

Latest

Requests for Research 2.0

Scaling Kubernetes to 2,500 nodes

Block-sparse GPU kernels

Learning sparse neural networks through L₀ regular...

Interpretable and pedagogical examples

Learning a hierarchy

Generalizing from simulation

Sim-to-real transfer of robotic control with dynam...

Asymmetric actor critic for image-based robot lear...

Domain randomization and generative models for rob...

Meta-learning for wrestling

Competitive self-play

Nonlinear computation in deep linear networks

Learning to model other minds

Learning with opponent-learning awareness

OpenAI Baselines: ACKTR & A2C

More on Dota 2

Dota 2

Trending

Popular

Gemini Robotics: Roboter-Durchbruch

AI as Normal Technology

Pokémon Go feiert Anime-Horizons-Event

Anthropic legt neue AI-Nutzungsdaten vor

Beyond chatbots: How to build agentic AI systems