Research map / Reinforcement learning / Visual and representation RL
Parameter Space Noise for Exploration
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 adaptive parameter-space noise to DQN | DQN · ALE games (15 of 21) | median return | Helped |
| Add adaptive parameter-space noise to DQN | DQN · Breakout | median return: 406.0 -> 390.5 | Hurt |
| Add adaptive parameter-space noise to DQN | DQN · Gravitar | median return: 300.0 -> 250.0 | Hurt |
| Add adaptive parameter-space noise to DQN | DQN · Pitfall | median return: -73.0 -> -100.0 | Hurt |
| Add adaptive parameter-space noise to DQN | DQN · MontezumaRevenge | median return: 0.0 -> 0.0 | No clear effect |
| Use parameter-space noise instead of action-space noise | DQN · Enduro and Freeway | return | Helped |
| Use parameter-space noise instead of action-space noise | DDPG · HalfCheetah | return | Helped |
| Use parameter-space noise instead of action-space noise | DDPG · SparseCartpoleSwingup | return | Helped |
| Use parameter-space noise instead of action-space noise | DDPG · SparseMountainCar | return | Helped |
| Use parameter-space noise instead of action-space noise | DDPG · SparseHalfCheetah | return | Mixed |
| Use parameter-space noise instead of action-space noise | DDPG · SwimmerGather | return | No clear effect |
| Use parameter-space noise instead of action-space noise | DDPG · remaining dense continuous-control tasks | return | No clear effect |
Closest papers by meaning
- Parameter Exploration for RLVR via Variational Learning (NeurIPS 2026 · similarity 0.91)
- Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards (NeurIPS 2026 · similarity 0.91)
- Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning (ICLR 2023 · similarity 0.90)
- Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling (AAAI 2024 · similarity 0.90)
- Noisy Networks For Exploration (ICLR 2018 · similarity 0.89)
- Emergence of In-Context Reinforcement Learning from Noise Distillation (ICML 2024 · similarity 0.88)
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.