CausalWorld: A Robotic Manipulation Benchmark
CausalWorld: A Robotic Manipulation Benchmark
CAUSALWORLD: A ROBOTIC MANIPULATION BENCHMARK FOR CAUSAL STRUCTURE AND TRANSFER LEARNING CausalWorld is an open-source simulation framework and benchmark for causal structure and transfer learning in a robotic manipulation environment (powered by bullet) where tasks range from rather simple to extremely hard. Tasks consist of constructing 3D shapes from a given set of blocks - inspired by how children learn to build complex structures. The release v1.2 supports many interesting goal shape families as well as exposing many causal variables in the environment to perform do_interventions on them. https://sites.google.com/view/causal-world/home https://github.com/rr-learning/CausalWorld https://causal-world.readthedocs.io/en/latest/index.html
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Incorrect prediction on native model
Similar products
The psychological war against AI manipulation
WebGL Sprites Benchmark
NAB – The Numenta Anomaly Benchmark
NAB – The Numenta Anomaly Benchmark
Image Manipulation via Triangulation
DOM registry for a better DOM Manipulation
String-fn – string manipulation library
A RIFF parsing and manipulation library
AgentMafia – A Social Deduction Benchmark
A New Implementation of the Seven GUIs Benchmark