# Enhance Exploration in Safe Reinforcement Learning with Contrastive Representation Learning

arXiv: https://arxiv.org/abs/2503.10318 · HTML: https://mlsanity.com/paper/2503.10318/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Placed in

- Deep reinforcement learning methods / [Safe and constrained RL](https://mlsanity.com/deeprl/safe-and-constrained-rl/)

## Builds on (most cited first, 20 of 20)

- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Improving Sample Efficiency in Model-Free Reinforcement Learning from Images](https://mlsanity.com/paper/1910.01741/) (2019)
- [Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model](https://mlsanity.com/paper/1907.00953/) (2019)
- [RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments](https://mlsanity.com/paper/2002.12292/) (2020)
- [Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients](https://mlsanity.com/paper/2109.13333/) (2021)
- [Learning to be Safe: Deep RL with a Safety Critic](https://mlsanity.com/paper/2010.14603/) (2020)
- [Safe Reinforcement Learning by Imagining the Near Future](https://mlsanity.com/paper/2202.07789/) (2022)
- [Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning](https://mlsanity.com/paper/1802.06480/) (2018)
- [Safe Reinforcement Learning Using Advantage-Based Intervention](https://mlsanity.com/paper/2106.09110/) (2021)
- [Return-Based Contrastive Representation Learning for Reinforcement Learning](https://mlsanity.com/paper/2102.10960/) (2021)
- [Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration](https://mlsanity.com/paper/2006.01419/) (2020)
- [Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation](https://mlsanity.com/paper/2210.01801/) (2022)
- [Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning](https://mlsanity.com/paper/2107.07316/) (2021)
- [Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning](https://mlsanity.com/paper/1909.04307/) (2019)
- [Feasibility Consistent Representation Learning for Safe Reinforcement Learning](https://mlsanity.com/paper/2405.11718/) (2024)

## Abstract (arXiv)

In safe reinforcement learning, agent needs to balance between exploration actions and safety constraints. Following this paradigm, domain transfer approaches learn a prior Q-function from the related environments to prevent unsafe actions. However, because of the large number of false positives, some safe actions are never executed, leading to inadequate exploration in sparse-reward environments. In this work, we aim to learn an efficient state representation to balance the exploration and safety-prefer action in a sparse-reward environment. Firstly, the image input is mapped to latent representation by an auto-encoder. A further contrastive learning objective is employed to distinguish safe and unsafe states. In the learning phase, the latent distance is used to construct an additional safety check, which allows the agent to bias the exploration if it visits an unsafe state. To verify the effectiveness of our method, the experiment is carried out in three navigation-based MiniGrid environments. The result highlights that our method can explore the environment better while maintaining a good balance between safety and efficiency.