Research map / Reinforcement learning / Imitation learning
Hybrid Policy Optimization from Imperfect Demonstrations
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 HYPO instead of PPO trained on sparse rewards | HYPO · sparse-reward MuJoCo | average episode return | Helped |
| use HYPO instead of GAIL | HYPO · sparse-reward MuJoCo | average episode return | Helped |
| use HYPO instead of POfD | HYPO · sparse-reward MuJoCo | average episode return | Helped |
| use HYPO instead of LOGO | HYPO · sparse-reward MuJoCo | average episode return | Helped |
| vary number and quality of imperfect demonstration trajectories | HYPO versus baselines · MuJoCo | final performance | Helped |
| use HYPO with imperfect demonstrations on sparse-reward tasks | HYPO · Google Research Football and AirSim UAV | return | Helped |
Closest papers by meaning
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.89)
- Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data (AAAI 2025 · similarity 0.88)
- Iterative Regularized Policy Optimization with Imperfect Demonstrations (ICML 2024 · similarity 0.88)
- Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration (ICLR 2025 · similarity 0.87)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.87)
- Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective (ICML 2025 · similarity 0.87)
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.