# Parameter Space Noise for Exploration

arXiv: https://arxiv.org/abs/1706.01905 · HTML: https://mlsanity.com/paper/1706.01905/

## Key facts

- Cited by 161 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2017.

## Built on by (most cited first, 30 of 161)

- [Exploration in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2205.00824/) (2022)
- [State Entropy Maximization with Random Encoders for Efficient Exploration](https://mlsanity.com/paper/2102.09430/) (2021)
- [A Survey of Exploration Methods in Reinforcement Learning](https://mlsanity.com/paper/2109.00157/) (2021)
- [Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain](https://mlsanity.com/paper/2109.06668/) (2021)
- [DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization](https://mlsanity.com/paper/2310.19668/) (2023)
- [PaCo: Parameter-Compositional Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2210.11653/) (2022)
- [Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers](https://mlsanity.com/paper/2510.00915/) (2025)
- [SAM as an Optimal Relaxation of Bayes](https://mlsanity.com/paper/2210.01620/) (2022)
- [MADE: Exploration via Maximizing Deviation from Explored Regions](https://mlsanity.com/paper/2106.10268/) (2021)
- [Sample-Efficient Imitation Learning via Generative Adversarial Nets](https://mlsanity.com/paper/1809.02064/) (2018)
- [Small batch deep reinforcement learning](https://mlsanity.com/paper/2310.03882/) (2023)
- [Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning](https://mlsanity.com/paper/2509.24372/) (2025)
- [Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement](https://mlsanity.com/paper/2110.07067/) (2021)
- [Evolutionary Reinforcement Learning: A Survey](https://mlsanity.com/paper/2303.04150/) (2023)
- [Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo](https://mlsanity.com/paper/2305.18246/) (2023)
- [Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction](https://mlsanity.com/paper/2504.15266/) (2025)
- [An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey](https://mlsanity.com/paper/2209.08890/) (2022)
- [Bayesian Sequential Optimal Experimental Design for Nonlinear Models Using Policy Gradient Reinforcement Learning](https://mlsanity.com/paper/2110.15335/) (2021)
- [A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals](https://mlsanity.com/paper/2408.05804/) (2024)
- [Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance](https://mlsanity.com/paper/2206.03787/) (2022)
- [Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration](https://mlsanity.com/paper/2305.19476/) (2023)
- [Latent Exploration for Reinforcement Learning](https://mlsanity.com/paper/2305.20065/) (2023)
- [Continuous Control with Coarse-to-fine Reinforcement Learning](https://mlsanity.com/paper/2407.07787/) (2024)
- [Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning](https://mlsanity.com/paper/2501.17827/) (2025)
- [Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns](https://mlsanity.com/paper/2503.03660/) (2025)
- [QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs](https://mlsanity.com/paper/2510.11696/) (2025)
- [Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning](https://mlsanity.com/paper/2006.16785/) (2020)
- [Derivative-Free Reinforcement Learning: A Review](https://mlsanity.com/paper/2102.05710/) (2021)
- [Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning](https://mlsanity.com/paper/2101.09458/) (2021)
- [Can Learned Optimization Make Reinforcement Learning Less Difficult?](https://mlsanity.com/paper/2407.07082/) (2024)

## Abstract (arXiv)

Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors. Methods such as evolutionary strategies use parameter perturbations, but discard all temporal structure in the process and require significantly more samples. Combining parameter noise with traditional RL methods allows to combine the best of both worlds. We demonstrate that both off- and on-policy methods benefit from this approach through experimental comparison of DQN, DDPG, and TRPO on high-dimensional discrete action environments as well as continuous control tasks. Our results show that RL with parameter noise learns more efficiently than traditional RL with action space noise and evolutionary strategies individually.