Research map / Reinforcement learning / Visual and representation RL
Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning
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 |
|---|---|---|---|
| Add PEER representation regularization to TD3 | TD3 · PyBullet | average return: PEER coupled with TD3 outperforms TD3 on all environments | Helped |
| Add PEER representation regularization to CURL | CURL · DMControl500k | score: 5 out of 6 tasks | Mixed |
| Add PEER representation regularization to CURL | CURL · DMControl100k | score: 6 out of 6 tasks | Helped |
| Add PEER representation regularization to DrQ | DrQ · Atari100k | score: 16 out of 26 games | Mixed |
| Add PEER representation regularization to CURL | CURL · Atari100k | score: 19 out of 26 games | Mixed |
| Use PEER to preserve distinguishable representations between the Q-network and target | TD3 · PyBullet | distinguishable representation discrepancy | Helped |
| Use PEER to preserve distinguishable representations between the Q-network and target | CURL · DMControl | distinguishable representation discrepancy | Helped |
Closest papers by meaning
- DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization (ICLR 2022 · similarity 0.88)
- Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation (ICLR 2024 · similarity 0.88)
- Regularization Matters in Policy Optimization - An Empirical Study on Continuous Control (ICLR 2021 · similarity 0.88)
- Shallow Updates for Deep Reinforcement Learning (NeurIPS 2017 · similarity 0.88)
- Online Laplacian-Based Representation Learning in Reinforcement Learning (ICML 2025 · similarity 0.86)
- Representation Learning Enables Scalable Multitask Deep Reinforcement Learning (NeurIPS 2026 · 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.