Random Latent Exploration For Deep Reinforcement Learning

Abstract

We introduce Random Latent Exploration (RLE), a simple yet effective exploration strategy in reinforcement learning (RL). On average, RLE outperforms noise-based methods, which perturb the agent's actions, and bonus-based exploration, which rewards the agent for attempting novel behaviors. The core idea of RLE is to encourage the agent to explore different parts of the environment by pursuing randomly sampled goals in a latent space. RLE is as simple as noise-based methods, as it avoids complex bonus calculations but retains the deep exploration benefits of bonus-based methods. Our experiments show that RLE improves performance on average in both discrete (e.g., Atari) and continuous control tasks (e.g., Isaac Gym), enhancing exploration while remaining a simple and general plug-in for existing RL algorithms. Project website and code: https://srinathm1359.github.io/random-latent-exploration

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymahankali2024random

Related papers

• Learning-driven Exploration For Reinforcement Learning (2019)6.45
• Fast Active Learning For Pure Exploration In Reinforcement Learning (2020)0.00
• Improving Policy Gradient By Exploring Under-appreciated Rewards (2016)0.00
• Parameter Space Noise For Exploration (2017)0.00
• Computationally Efficient Reinforcement Learning: Targeted Exploration Leveraging Simple Rules (2022)2.26
• Exploring More When It Needs In Deep Reinforcement Learning (2021)0.00
• Exploration By Random Distribution Distillation (2025)0.00
• Rlexplore: Accelerating Research In Intrinsically-motivated Reinforcement Learning (2024)5.33