Research map / Reinforcement learning / Visual and representation RL
Spectral Decomposition Representation for Reinforcement Learning
Tongzheng Ren, Tianjun Zhang, Lisa Lee, Joseph E. Gonzalez, Dale Schuurmans, Bo Dai
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 |
|---|---|---|---|
| Replace state-only spectral features with policy-independent state-action SPEDER features with optimism bonus | online RL on sparse-reward DeepMind Control tasks · DeepMind Control Suite (sparse reward) | return | Improved |
| Use SPEDER features (vs. SAC with 3-layer critic) on dense-reward MuJoCo | online RL on MuJoCo · MBBL MuJoCo tasks | return | Mixed |
| Imitation with SPEDER latent behavioral cloning | AntMaze imitation learning · D4RL AntMaze | average return | No clear effect |
| Remove the exploration bonus / optimism from SPEDER (ablation) | SPEDER online exploration · DeepMind Control Suite (sparse reward) | return | No clear effect |
Closest papers by meaning
- Diffusion Spectral Representation for Reinforcement Learning (NeurIPS 2024 · similarity 0.91)
- Online Laplacian-Based Representation Learning in Reinforcement Learning (ICML 2025 · similarity 0.88)
- Proper Laplacian Representation Learning (ICLR 2024 · similarity 0.87)
- Towards Principled Representation Learning from Videos for Reinforcement Learning (ICLR 2024 · similarity 0.87)
- Bridging State and History Representations: Understanding Self-Predictive RL (ICLR 2024 · similarity 0.87)
- BeigeMaps: Behavioral Eigenmaps for Reinforcement Learning from Images (ICML 2024 · 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.
