Research map / Reinforcement learning / Visual and representation RL
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning
Hojoon Lee, Hanseul Cho, Hyunseung Kim, Daehoon Gwak, Joonkee Kim, Jaegul Choo, Se-Young Yun, Chulhee Yun
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 |
|---|---|---|---|
| add Reset to DrQ | DrQ · Atari-100k | IQM: 0.258 -> 0.343 | Improved |
| add SAM to DrQ | DrQ · Atari-100k | IQM: 0.258 -> 0.325 | Improved |
| add LN to DrQ | DrQ · Atari-100k | IQM: 0.258 -> 0.259 | No clear effect |
| add CReLU to DrQ | DrQ · Atari-100k | IQM: 0.258 -> 0.256 | No clear effect |
| combine LN, SAM, CReLU and Reset (PLASTIC) | DrQ · Atari-100k | IQM: 0.343 -> 0.421 | Improved |
| combine all four methods (PLASTIC) | DrQ · DMC-M | IQM: 213 -> 565 | Improved |
| add LN to DrQ | DrQ · DMC-M | IQM: 213 -> 412 | Improved |
| add CReLU to LN (ablation) | LN · Atari-100k | IQM: 0.259 -> 0.284 | Improved |
| add Reset to LN (ablation) | LN · Atari-100k | IQM: 0.259 -> 0.396 | Improved |
| add SAM to Reset (ablation) | Reset · Atari-100k | IQM: 0.343 -> 0.411 | Improved |
| add SAM and Reset to SimTPR fine-tuning at RR 4 | SimTPR · Atari-100k | IQM: 0.243 -> 0.834 | Improved |
| add SAM on top of Reset in pretrained SimTPR at RR 2 | SimTPR · Atari-100k | IQM: 0.709 -> 0.776 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PlayVirtual — PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning (NeurIPS 2021) · 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
- Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages (ICLR 2024 · similarity 0.91)
- A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning (ICML 2024 · similarity 0.86)
- Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn (ICML 2025 · similarity 0.86)
- Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity (ICLR 2024 · similarity 0.85)
- EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data (ICML 2024 · similarity 0.85)
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.
