Research map / Reinforcement learning / Visual and representation RL
One Encoder to Rule them All: Representation Learning for Model-free Visual Reinforcement Learning using Fourier Neural Operators
Parag Dutta, Mohd Ayyoob, Shalabh Bhatnagar, Ambedkar Dukkipati
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 CNN encoder with FNO encoder | Efficient Rainbow · Atari100K | median HNS: 16.14 -> 26.11 | Improved |
| replace CNN encoder with FNO encoder | Efficient Rainbow · Atari100K | games won: 20/26 games | Improved |
| replace CNN encoder with FNO encoder | R-BVE · Atari offline 1% DQN Replay | HNS %: 2.89x vs DT | Improved |
| replace CNN encoder with FNO encoder | R-BVE · Atari offline Breakout | HNS %: 110.5 -> 555.1 | Improved |
| replace CNN encoder with FNO encoder | PPO · CARLA Lane | normalized score: 100 ± 0.03 | Improved |
| replace MLP encoder with FNO encoder (ablation) | SAC · DMC state-based (6 tasks) | median normalized score | Improved |
| change learning rate, gamma or add random cropping (ablation) | FNO-PPO · CARLA Lane | reward | Hurt |
| increase test image size from 84x84 to 128x128 without retraining (ablation) | FNO + Eff. RB · Atari100K | median HNS: 26.11 -> 26.10 | No clear effect |
| increase test image size from 48x48 to 224x224 without retraining (ablation) | FNO-PPO · CARLA Lane | normalized score: ~0.8 | No clear effect |
| replace CNN encoder with FNO encoder | Efficient Rainbow · Atari100K | mean HNS ratio: 6.04x | Improved |
| replace CNN encoder with FNO encoder | Efficient Rainbow · Atari100K Seaquest | HNS %: 0.75 vs 0.75 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- CURL — CURL: Contrastive Unsupervised Representations for Reinforcement Learning (ICML 2020) · better on 5 of 6 shared results
- Rainbow — Rainbow: Combining Improvements in Deep Reinforcement Learning (AAAI 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability (NeurIPS 2023 · similarity 0.87)
- Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning (NeurIPS 2022 · similarity 0.87)
- Efficient Reinforcement Learning Through Adaptively Pretrained Visual Encoder (AAAI 2025 · similarity 0.86)
- Zero-Shot Reinforcement Learning via Function Encoders (ICML 2024 · similarity 0.86)
- Towards Principled Representation Learning from Videos for Reinforcement Learning (ICLR 2024 · similarity 0.86)
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.
