Research map / Reinforcement learning / MDPs and planning
Generation of Policy-Level Explanations for Reinforcement Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 APG Gen to infer important features from transitions covering 10% of non-terminal states | APG Gen · PrereqWorld (m=15) | feature classification accuracy: over 93% | Helped |
| Use APG Gen with transitions covering 80% of non-terminal states | APG Gen · PrereqWorld (m=15), deterministic and stochastic environments | feature classification accuracy: 98.7% | Helped |
| Predict actions multiple steps ahead using the APG Markov assumption | APG Gen · PrereqWorld (m=15), stochastic domains | action prediction agreement | Mixed |
| Represent the policy as an APG rather than a grounded-state Markov chain | APG Gen · PrereqWorld | explanation size: 32 to 1,073,741,824 | Helped |
Closest papers by meaning
- Explainable Reinforcement Learning via Model Transforms (NeurIPS 2022 · similarity 0.91)
- Local Explanations for Reinforcement Learning (AAAI 2023 · similarity 0.90)
- ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies (NeurIPS 2026 · similarity 0.87)
- Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning (AAAI 2025 · similarity 0.87)
- Explaining Reinforcement Learning Agents through Counterfactual Action Outcomes (AAAI 2024 · similarity 0.86)
- The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space (NeurIPS 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.