Research map / Reinforcement learning / Imitation learning
Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning
Xin-Qiang Cai, Yao-Xiang Ding, Zixuan Chen, Yuan Jiang, Masashi Sugiyama, Zhi-Hua Zhou
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 |
|---|---|---|---|
| add importance weighting to GAIL | GAIL · Atari and MuJoCo | return | Improved |
| compare GAIL and IW with pi_1 | GAIL, IW · Atari and MuJoCo | return | No clear effect |
| third-person IL under heterogeneous observations | TPIL · Hopper, Swimmer, Walker2d | return | Hurt |
| GAMA mapping under support mismatch | GAMA · Hopper and Walker2d | return | Hurt |
| LBC with privileged O_E in Atari | LBC · Atari | return | Improved |
| LBC when O_E is not more privileged than O_L | LBC · most MuJoCo environments | return | Hurt |
| use IWRE with rejection and limited queries | IWRE · 8 environments | return: 6/8 | Improved |
| compare IWRE with PPO on true rewards under RAM input | PPO-RAM · Atari RAM | return | Improved |
| add random queries to GAIL (ablation) | GAIL-Rand · Hopper, Swimmer, Walker2d | return | Hurt |
| add random queries to IW (ablation) | IW-Rand · Hopper, Reacher, Walker2d | return | Improved |
| increase query budget for TPIL (ablation) | TPIL · Swimmer and Walker2d | return | Mixed |
| increase query budget for IWRE (ablation) | IWRE · MuJoCo | return | Improved |
Closest papers by meaning
- Deep Demonstration Tracing: Learning Generalizable Imitator Policy for Runtime Imitation from a Single Demonstration (ICML 2024 · similarity 0.89)
- OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning (ICML 2024 · similarity 0.89)
- Imitation from Observations with Trajectory-Level Generative Embeddings (NeurIPS 2026 · similarity 0.89)
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning (NeurIPS 2024 · similarity 0.88)
- Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning (NeurIPS 2025 · similarity 0.88)
- Causal Imitation for Markov Decision Processes: a Partial Identification Approach (NeurIPS 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.
