Research map / Reinforcement learning / Imitation learning
Active Exploration for Inverse 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 full AceIRL instead of AceIRL Greedy (ablation) | AceIRL · Four Paths N_E=50 | samples to regret < 0.4: 24180 -> 10780 | Helped |
| use full AceIRL instead of AceIRL Greedy (ablation) | AceIRL · Double Chain N_E=50 | samples to regret < 0.4: 16240 -> 11580 | Helped |
| use full AceIRL instead of AceIRL Greedy (ablation) | AceIRL · Chain N_E=1 | samples to regret < 0.4: 153 -> 142 | Helped |
| use full AceIRL instead of AceIRL Greedy (ablation) | AceIRL · Gridworld N_E=1 | samples to regret < 0.4: 46 -> 48 | No clear effect |
| use AceIRL Greedy instead of random exploration | AceIRL Greedy · Four Paths N_E=50 | samples to regret < 0.4: 17840 -> 24180 | Hurt |
| increase N_E from 50 to 200 | AceIRL · Four Paths | samples to regret < 0.4: 10780 -> 16160 | Hurt |
| increase N_E from 50 to 200 | AceIRL · Double Chain | samples to regret < 0.4: 11580 -> 20400 | Hurt |
| increase N_E from 50 to 200 | AceIRL Greedy · Four Paths | samples to regret < 0.4: 24180 -> 52000 | Hurt |
| increase N_E from 50 to 200 | AceIRL Greedy · Double Chain | samples to regret < 0.4: 16240 -> 37200 | Hurt |
| use AceIRL instead of random exploration | AceIRL · Four Paths N_E=50 | samples to regret < 0.4: 17840 -> 10780 | Helped |
| use AceIRL instead of random exploration | AceIRL · Double Chain N_E=50 | samples to regret < 0.4: 23640 -> 11580 | Helped |
| use AceIRL instead of random exploration | AceIRL · Chain N_E=1 | samples to regret < 0.4: 161 -> 142 | Helped |
Closest papers by meaning
- Recent Advancements in Inverse Reinforcement Learning (AAAI 2024 · similarity 0.93)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.92)
- Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms (ICML 2024 · similarity 0.91)
- Environment Design for Inverse Reinforcement Learning (ICML 2024 · similarity 0.90)
- How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach (NeurIPS 2024 · similarity 0.90)
- Provably Efficient Exploration in Inverse Constrained Reinforcement Learning (ICML 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.