Research map / Reinforcement learning / Imitation learning
Deep PQR: Solving Inverse Reinforcement Learning using Anchor Actions
Sinong Geng, Houssam Nassif, Carlos Manzanares, Max Reppen, Ronnie Sircar
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 anchor-action identification and sequential policy, Q-function, and reward estimation | PQR · Synthetic Q recovery | Q-function estimation accuracy | Improved |
| Use anchor-action identification and sequential policy, Q-function, and reward estimation | PQR · Synthetic Q recovery, early training | Q-function estimation accuracy | Hurt |
| Use the anchor-action reward information to estimate rewards | PQR · Synthetic reward recovery | reward estimation accuracy | Improved |
| Use PQR rather than SPL-GD for behavior prediction | Airline market entry · Airline market entry | negative log-likelihood | Improved |
| Increase the number of non-stop competitors | Most airline companies · Airline market entry counterfactual analysis | market entry likelihood | Hurt |
| Increase the number of non-stop competitors | American Airlines · Airline market entry counterfactual analysis | market entry likelihood | Improved |
Closest papers by meaning
- Deep Inverse Q-learning with Constraints (NeurIPS 2020 · similarity 0.90)
- Recovering Hidden Reward in Diffusion-Based Policies (ICML 2026 · similarity 0.90)
- Inverse Reinforcement Learning from a Gradient-based Learner (NeurIPS 2020 · similarity 0.89)
- A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning (NeurIPS 2026 · similarity 0.88)
- Inverting the Bellman Equation: From $Q$-Values to World Models (NeurIPS 2026 · similarity 0.88)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.88)
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.
