Research map / Reinforcement learning / Visual and representation RL
Learning Representations via a Robust Behavioral Metric for Deep Reinforcement Learning
Jianda Chen, Sinno Pan
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 |
|---|---|---|---|
| use RAP behavioral metric instead of DrQ augmentation | SAC · Robosuite Door Opening | episode return: 14.63 -> 102.19 | Improved |
| use RAP instead of DBC | SAC · Robosuite Two Arm Peg-In-Hole | episode return: 219.56 -> 307.27 | Improved |
| use RAP instead of MICo | SAC · Robosuite Door Opening | episode return: 6.06 -> 102.19 | Improved |
| add RAP representation loss to plain SAC | SAC · Robosuite Door Opening | episode return: 8.84 -> 102.19 | Improved |
| add RAP loss vs plain SAC | SAC · Robosuite Two Arm Peg-In-Hole | episode return: 191.29 -> 307.27 | Improved |
| compare RAP with DrQ augmentation | SAC · DMC original background | episode return | No clear effect |
| use RAP vs DBC and MICo with natural video background | SAC · DMC natural video background | episode return | Improved |
| compare RAP with DrQ with natural video background | SAC · DMC natural video background | episode return | Mixed |
| use RAP vs DBC and MICo | SAC · CARLA | episode return | Improved |
| compare RAP with DrQ | SAC · CARLA | episode return | No clear effect |
Closest papers by meaning
- State Chrono Representation for Enhancing Generalization in Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
- BeigeMaps: Behavioral Eigenmaps for Reinforcement Learning from Images (ICML 2024 · similarity 0.86)
- Representation Learning Enables Scalable Multitask Deep Reinforcement Learning (NeurIPS 2026 · similarity 0.84)
- Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation (ICLR 2024 · similarity 0.84)
- Deep Reinforcement Learning with Time-Scale Invariant Memory (AAAI 2025 · similarity 0.84)
- DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors (NeurIPS 2024 · similarity 0.84)
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.
