Research map / Reinforcement learning / Imitation learning
Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills
Denis Blessing, Onur Celik, Xiaogang Jia, Moritz Reuss, Maximilian Xiling Li, Rudolf Lioutikov, Gerhard Neumann
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train mixture of experts with IMC instead of EM | mixture of experts · Obstacle Avoidance | success rate: 0.675 -> 0.855 | Improved |
| train mixture of experts with IMC instead of EM | mixture of experts · Obstacle Avoidance | entropy: 0.902 -> 0.930 | Improved |
| train mixture of experts with IMC instead of EM | mixture of experts · Block Pushing | success rate: 0.458 -> 0.521 | Improved |
| train mixture of experts with IMC instead of EM | mixture of experts · Block Pushing | entropy: 0.707 -> 0.654 | Hurt |
| train mixture of experts with IMC instead of EM | mixture of experts · Table Tennis | distance error: 0.220 -> 0.153 | Improved |
| train mixture of experts with IMC instead of EM | mixture of experts · Table Tennis | success rate: 0.725 -> 0.870 | Improved |
| use IMC instead of DDPM | policy · Table Tennis | distance error: 0.185 -> 0.153 | Improved |
| use IMC instead of CVAE | policy · Obstacle Avoidance | entropy: 0.465 -> 0.930 | Improved |
| use IMC instead of CVAE | policy · Obstacle Avoidance | success rate: 0.853 -> 0.855 | No clear effect |
| use IMC instead of BET | policy · Obstacle Avoidance | success rate: 0.504 -> 0.855 | Improved |
| use IMC instead of ML-Cur | policy · Block Pushing | success rate: 0.000 -> 0.521 | Improved |
| vary number of components for IMC vs EM (1 to 50), few components (ablation) | IMC vs EM · Obstacle Avoidance / Table Tennis | success rate | Improved |
Closest papers by meaning
- Curriculum Design for Teaching via Demonstrations: Theory and Applications (NeurIPS 2021 · similarity 0.88)
- Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation (NeurIPS 2026 · similarity 0.87)
- How to Leverage Diverse Demonstrations in Offline Imitation Learning (ICML 2024 · similarity 0.86)
- Data Scaling Laws in Imitation Learning for Robotic Manipulation (ICLR 2025 · similarity 0.86)
- Imitation from Observations with Trajectory-Level Generative Embeddings (NeurIPS 2026 · similarity 0.86)
- Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts (ICML 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
