Research map / Reinforcement learning / Imitation learning
Inverse Reinforcement Learning from a Gradient-based Learner
Giorgia Ramponi, Gianluca Drappo, Marcello Restelli
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 LOGEL instead of LfL to infer reward weights from G(PO)MDP learning | GridWorld · GridWorld, G(PO)MDP learner | reward-weight recovery | Improved |
| Use LOGEL instead of LfL to infer reward weights from Q-learning | GridWorld · GridWorld, Q-learning learner | learning steps needed for reward-weight recovery | Improved |
| Use LOGEL instead of LfL to infer reward weights from SVI | GridWorld · GridWorld, SVI learner | learning steps needed for reward-weight recovery | Improved |
| Use LOGEL instead of LfL to infer reward weights from PPO learning | MuJoCo Hopper · Hopper | effectiveness of recovered reward | Improved |
| Use LOGEL to infer reward weights from PPO learning | MuJoCo Reacher · Reacher | learning speed | Hurt |
| Estimate gradients from more trajectories | LOGEL · GridWorld, G(PO)MDP learner | reward-weight recovery | Improved |
| Observe more policy-improvement steps when gradient estimates are noisy | LOGEL · GridWorld, G(PO)MDP learner | reward-weight recovery | Improved |
| Apply LOGEL to learners using algorithms other than gradient-based ones | LOGEL · GridWorld | reward-weight recovery | Improved |
Closest papers by meaning
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.92)
- Recent Advancements in Inverse Reinforcement Learning (AAAI 2024 · similarity 0.91)
- Environment Design for Inverse Reinforcement Learning (ICML 2024 · similarity 0.91)
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.91)
- 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 0.90)
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.
