Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Noisy Networks 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 |
|---|---|---|---|
| Replace ε-greedy with learned noisy weights in DQN | DQN · Atari 57 games | median human-normalised score: 83 -> 123 | Helped |
| Replace ε-greedy with learned noisy weights in Dueling | Dueling · Atari 57 games | median human-normalised score: 132 -> 172 | Helped |
| Replace entropy bonus with learned noisy weights in A3C | A3C · Atari 57 games | median human-normalised score: 80 -> 94 | Helped |
| Use factorised rather than independent Gaussian noise (ablation) | NoisyNet-A3C · Atari 57 games | median human-normalised score: 94 -> 99 | Helped |
| Use factorised rather than independent Gaussian noise (ablation) | NoisyNet-A3C · Atari 57 games | mean human-normalised score: 347 -> 276 | Hurt |
Closest papers by meaning
- Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling (AAAI 2024 · similarity 0.86)
- Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards (NeurIPS 2026 · similarity 0.85)
- Confounding Robust Deep Reinforcement Learning: A Causal Approach (NeurIPS 2025 · similarity 0.85)
- Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning (ICML 2025 · similarity 0.84)
- Parameter Exploration for RLVR via Variational Learning (NeurIPS 2026 · similarity 0.84)
- Random Latent Exploration for Deep Reinforcement Learning (ICML 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.