Research map / Reinforcement learning / Visual and representation RL
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
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 SeCTAR with latent-space planning and exploration instead of the compared methods | 2D navigation · 2D navigation | reward | Helped |
| Use SeCTAR with latent-space planning and exploration instead of the compared methods | Wheeled locomotion · wheeled locomotion | reward | Helped |
| Use SeCTAR with latent-space planning and exploration instead of the compared methods | Object manipulation · object manipulation | reward | Helped |
| Use SeCTAR with latent-space planning and exploration instead of the compared methods | Swimmer navigation · swimmer navigation | reward | Helped |
| Train an explorer with the negative-ELBO trajectory exploration objective | SeCTAR explorer · 2D navigation | state-space coverage | Helped |
| Train an explorer with the negative-ELBO trajectory exploration objective | SeCTAR explorer · wheeled locomotion | state-space coverage | Helped |
| Train an explorer with the negative-ELBO trajectory exploration objective | SeCTAR explorer · object manipulation | object-state coverage | Helped |
| Omit the state decoder's policy-generated-trajectory likelihood term (ablation) | SeCTAR · trajectory model training | model performance | No clear effect |
Closest papers by meaning
- Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models (NeurIPS 2025 · similarity 0.88)
- Improving Unsupervised Hierarchical Representation with Reinforcement Learning (CVPR 2024 · similarity 0.88)
- Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference (NeurIPS 2024 · similarity 0.88)
- Reasoning with Latent Diffusion in Offline Reinforcement Learning (ICLR 2024 · similarity 0.88)
- Trajectory-Class-Aware Multi-Agent Reinforcement Learning (ICLR 2025 · similarity 0.88)
- State-Covering Trajectory Stitching for Diffusion Planners (NeurIPS 2025 · 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.