CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
Source
- Raw Markdown: paper_causalworld-2020.md
- PDF: paper_causalworld-2020.pdf
Core Claim
CausalWorld provides robotic manipulation environments with interventions for causal structure and transfer learning.
Action-Time-Series Notes
- The time-series unit is simulated robot manipulation under actions and environment/task interventions.
- It is better for causal generalization tests than for real-world pretraining scale.
- It should be treated as a benchmark/environment source rather than a static logged dataset unless trajectories are generated.