Research map / Reinforcement learning / Visual and representation RL
Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning
Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao
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 |
|---|---|---|---|
| use GRADER instead of baselines (SAC, ICIN, PETS, TICSA, ICIL, GNN) | goal-conditioned RL · Stack, Unlock, Crash (I, S, C) | success rate | Improved |
| collect causal discovery data with the learned policy instead of an offline random policy (ablation) | GRADER · causal graph discovery (SHD) | causal graph accuracy | Improved |
| constraint-based data-efficient discovery instead of score-based soft adjacency matrix (ablation) | GRADER · Chemistry and task success | success rate and discovery accuracy | Improved |
| use learned causal graph instead of fixed full graph (ablation) | GRADER · nine tasks, especially spuriousness | success rate | Improved |
| make fixed causal graph more correct (from full graph toward best graph) (ablation) | GRADER · Unlock-S | reward | Improved |
| use GRADER instead of Score | causal discovery · Chemistry (Collider, Chain, Jungle, Full) | classification error metrics | Improved |
Closest papers by meaning
- Generalization of RLVR Using Causal Reasoning as a Testbed (ICLR 2026 · similarity 0.91)
- Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations (ICLR 2025 · similarity 0.90)
- Hierarchical Reinforcement Learning with Targeted Causal Interventions (ICML 2025 · similarity 0.89)
- Horizon Generalization in Reinforcement Learning (ICLR 2025 · similarity 0.88)
- Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning (ICML 2024 · similarity 0.88)
- Teaching Transformers Causal Reasoning through Axiomatic Training (ICML 2025 · 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.
