Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
Sumedh A Sontakke, Arash Mehrjou, Laurent Itti, Bernhard Schölkopf
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 |
|---|---|---|---|
| Pre-train the planner with causal curiosity before fine-tuning on a downstream task | Causal curiosity planner · Lifting | training convergence | Improved |
| Pre-train the planner with causal curiosity before fine-tuning on a downstream task | Causal curiosity planner · Travel | training convergence | Improved |
| Add the causal curiosity reward while optimizing the external task reward (ablation) | Causal curiosity planner · Lifting and Travel | downstream task performance | Hurt |
| Provide learned causal representations as policy inputs | PPO policy · TransferMass and TransferSizeMass | zero-shot generalization | Improved |
| Use self-supervised causal-curiosity experiments instead of supervised planners | Experiment planner · Downstream behavior pre-training | data efficiency: approximately 2.5 times less data | Improved |
| Provide only the z coordinate to the curiosity module (ablation) | Causal curiosity experiment planner · Causal World block experiments | behavior relevance to supplied coordinate | Improved |
| Provide only the x coordinate to the curiosity module (ablation) | Causal curiosity experiment planner · Causal World block experiments | behavior relevance to supplied coordinate | Improved |
Closest papers by meaning
- Curious Causality-Seeking Agents Learn Meta Causal World (NeurIPS 2025 · similarity 0.90)
- Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations (CVPR 2025 · similarity 0.89)
- Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations (ICLR 2025 · similarity 0.88)
- Hierarchical Reinforcement Learning with Targeted Causal Interventions (ICML 2025 · similarity 0.88)
- Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation (ICML 2024 · similarity 0.87)
- Can In-Context Learning Support Intrinsic Curiosity? (NeurIPS 2026 · similarity 0.87)
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.
