Research map / Reinforcement learning / Imitation learning
Imitating Latent Policies from Observation
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 |
|---|---|---|---|
| Learn a latent policy from expert state observations, then align latent actions with real actions using a small number of environment interactions | ILPO · Cartpole | imitation reward | Helped |
| Learn a latent policy from expert state observations, then align latent actions with real actions using a small number of environment interactions | ILPO · Acrobot | imitation reward | Helped |
| Learn a latent policy from expert state observations, then align latent actions with real actions using a small number of environment interactions | ILPO · Mountain car | imitation reward | Helped |
| Learn a latent policy from expert state observations, then align latent actions with real actions using a small number of environment interactions | ILPO · CoinRun easy | imitation reward | Helped |
| Learn a latent policy from expert state observations, then align latent actions with real actions using a small number of environment interactions | ILPO · CoinRun hard | imitation reward | Helped |
| Use one latent action (|Z|=1) (ablation) | ILPO · Cartpole and Acrobot | imitation reward | Hurt |
| Use deterministic rather than stochastic demonstrations (ablation) | ILPO · Cartpole and Acrobot | imitation reward | Hurt |
Closest papers by meaning
- Imitation Learning from Observation with Automatic Discount Scheduling (ICLR 2024 · similarity 0.89)
- Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations (NeurIPS 2025 · similarity 0.88)
- Efficient Imitation under Misspecification (ICLR 2025 · similarity 0.88)
- LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching (NeurIPS 2026 · similarity 0.88)
- Causal Imitation for Markov Decision Processes: a Partial Identification Approach (NeurIPS 2024 · similarity 0.88)
- Learning to Act without Actions (ICLR 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.