Research map / Reinforcement learning / Imitation learning
Inverse Reinforcement Learning through Policy Gradient Minimization
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 closed-form plane/null-space solution (PGIRL) instead of iterative convex optimization (GIRL) (ablation) | linear-reward IRL · 5D LQR, 1000 episodes | computation time (s): 257.4 -> 1.640 | Helped |
| add a baseline to REINFORCE/GPOMDP gradient estimates (ablation) | GIRL · 2D LQR | weight error (L-inf) | Helped |
| increase number of expert trajectories (ablation) | GIRL/PGIRL · LQR 5D,10D,20D | weight error (L-inf) | Helped |
| choice among RB, GB and eNAC gradient estimators (ablation) | GIRL · LQR 5D,10D,20D | weight error (L-inf) | No clear effect |
| use 3-degree polynomial approximation of the expert policy instead of exact linear form (ablation) | PGIRL · 1D LQR | weight error (L-inf) | No clear effect |
| use Gaussian RBF approximation of the expert policy (ablation) | PGIRL with eNAC · 1D LQR | weight error (L-inf) | Hurt |
| use PGIRL instead of CSI, SCIRL, REPS or classifier | mountain car IRL · Mountain Car | mean episode length | Mixed |
Closest papers by meaning
- Recent Advancements in Inverse Reinforcement Learning (AAAI 2024 · similarity 0.92)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.91)
- Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning (NeurIPS 2026 · similarity 0.90)
- Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms (ICML 2024 · similarity 0.90)
- Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching (ICLR 2025 · similarity 0.89)
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.