# Learning Object-conditioned Exploration using Distributed Soft Actor Critic

arXiv: https://arxiv.org/abs/2007.14545 · HTML: https://mlsanity.com/paper/2007.14545/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Diffusion-based Generation, Optimization, and Planning in 3D Scenes](https://mlsanity.com/paper/2301.06015/) (2023)
- [Open-vocabulary Queryable Scene Representations for Real World Planning](https://mlsanity.com/paper/2209.09874/) (2022)
- [How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers](https://mlsanity.com/paper/2305.16925/) (2023)
- [Stubborn: A Strong Baseline for Indoor Object Navigation](https://mlsanity.com/paper/2203.07359/) (2022)
- [RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation](https://mlsanity.com/paper/2405.05792/) (2024)
- [TANGO: Traversability-Aware Navigation with Local Metric Control for Topological Goals](https://mlsanity.com/paper/2509.08699/) (2025)
- [A Contextual Bandit Approach for Learning to Plan in Environments with Probabilistic Goal Configurations](https://mlsanity.com/paper/2211.16309/) (2022)
- [Task-Driven Graph Attention for Hierarchical Relational Object Navigation](https://mlsanity.com/paper/2306.13760/) (2023)
- [Weber-Fechner Law in Temporal Difference learning derived from Control as Inference](https://mlsanity.com/paper/2412.21004/) (2024)
- [Effective Reinforcement Learning Control using Conservative Soft Actor-Critic](https://mlsanity.com/paper/2505.03356/) (2025)
- [Model Adaptation for Time Constrained Embodied Control](https://mlsanity.com/paper/2406.11128/) (2024)

## Abstract (arXiv)

Object navigation is defined as navigating to an object of a given label in a complex, unexplored environment. In its general form, this problem poses several challenges for Robotics: semantic exploration of unknown environments in search of an object and low-level control. In this work we study object-guided exploration and low-level control, and present an end-to-end trained navigation policy achieving a success rate of 0.68 and SPL of 0.58 on unseen, visually complex scans of real homes. We propose a highly scalable implementation of an off-policy Reinforcement Learning algorithm, distributed Soft Actor Critic, which allows the system to utilize 98M experience steps in 24 hours on 8 GPUs. Our system learns to control a differential drive mobile base in simulation from a stack of high dimensional observations commonly used on robotic platforms. The learned policy is capable of object-guided exploratory behaviors and low-level control learned from pure experiences in realistic environments.