# Learning Vision-based Pursuit-Evasion Robot Policies

arXiv: https://arxiv.org/abs/2308.16185 · HTML: https://mlsanity.com/paper/2308.16185/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 60 references that are in the map.
- First posted on arXiv 30 Aug 2023.

## Builds on (most cited first, 30 of 32)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Learning by Cheating](https://mlsanity.com/paper/1912.12294/) (2019)
- [Learning High-Speed Flight in the Wild](https://mlsanity.com/paper/2110.05113/) (2021)
- [Learning Latent Representations to Influence Multi-Agent Interaction](https://mlsanity.com/paper/2011.06619/) (2020)
- [Fast Traversability Estimation for Wild Visual Navigation](https://mlsanity.com/paper/2305.08510/) (2023)
- [Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real](https://mlsanity.com/paper/1908.05224/) (2019)
- [Iterative Residual Policy: for Goal-Conditioned Dynamic Manipulation of Deformable Objects](https://mlsanity.com/paper/2203.00663/) (2022)
- [End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning](https://mlsanity.com/paper/1808.03405/) (2018)
- [Multimodal Sensor Fusion with Differentiable Filters](https://mlsanity.com/paper/2010.13021/) (2020)
- [ISAACS: Iterative Soft Adversarial Actor-Critic for Safety](https://mlsanity.com/paper/2212.03228/) (2022)
- [Learning Visual Locomotion with Cross-Modal Supervision](https://mlsanity.com/paper/2211.03785/) (2022)
- [Influencing Towards Stable Multi-Agent Interactions](https://mlsanity.com/paper/2110.08229/) (2021)
- [Stochastic Dynamic Games in Belief Space](https://mlsanity.com/paper/1909.06963/) (2019)
- [Safe Occlusion-aware Autonomous Driving via Game-Theoretic Active Perception](https://mlsanity.com/paper/2105.08169/) (2021)
- [Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning](https://mlsanity.com/paper/2210.04435/) (2022)
- [Learning to Interactively Learn and Assist](https://mlsanity.com/paper/1906.10187/) (2019)
- [Influencing Long-Term Behavior in Multiagent Reinforcement Learning](https://mlsanity.com/paper/2203.03535/) (2022)
- [RSPT: Reconstruct Surroundings and Predict Trajectories for Generalizable Active Object Tracking](https://mlsanity.com/paper/2304.03623/) (2023)
- [Steering a Predator Robot using a Mixed Frame/Event-Driven Convolutional Neural Network](https://mlsanity.com/paper/1606.09433/) (2016)
- [Learning Representations that Enable Generalization in Assistive Tasks](https://mlsanity.com/paper/2212.03175/) (2022)
- [Multi-robot Cooperative Pursuit via Potential Field-Enhanced Reinforcement Learning](https://mlsanity.com/paper/2203.04700/) (2022)
- [RILI: Robustly Influencing Latent Intent](https://mlsanity.com/paper/2203.12705/) (2022)
- [Learning Agile Locomotion via Adversarial Training](https://mlsanity.com/paper/2008.00603/) (2020)

## Built on by (most cited first, 11 of 11)

- [TrackVLA: Embodied Visual Tracking in the Wild](https://mlsanity.com/paper/2505.23189/) (2025)
- [Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL](https://mlsanity.com/paper/2404.09857/) (2024)
- [TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking](https://mlsanity.com/paper/2510.07134/) (2025)
- [EgoPet: Egomotion and Interaction Data from an Animal's Perspective](https://mlsanity.com/paper/2404.09991/) (2024)
- [Conformal Policy Learning for Sensorimotor Control Under Distribution Shifts](https://mlsanity.com/paper/2311.01457/) (2023)
- [Towards Task-Oriented Flying: Framework, Infrastructure, and Principles](https://mlsanity.com/paper/2504.15129/) (2025)
- [HEADER: Hierarchical Robot Exploration via Attention-Based Deep Reinforcement Learning with Expert-Guided Reward](https://mlsanity.com/paper/2510.15679/) (2025)
- [CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking](https://mlsanity.com/paper/2607.15004/) (2026)
- [CST-WM: A Causally Structured World Model for Embodied Visual Tracking](https://mlsanity.com/paper/2609.06302/) (2026)
- [Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning](https://mlsanity.com/paper/2609.27312/) (2026)
- [Memory-State Critic for Asymmetric Actor-Critic with Application to Vision-Based Pursuit-Evasion](https://mlsanity.com/paper/2610.03830/) (2026)

## Abstract (arXiv)

Learning strategic robot behavior -- like that required in pursuit-evasion interactions -- under real-world constraints is extremely challenging. It requires exploiting the dynamics of the interaction, and planning through both physical state and latent intent uncertainty. In this paper, we transform this intractable problem into a supervised learning problem, where a fully-observable robot policy generates supervision for a partially-observable one. We find that the quality of the supervision signal for the partially-observable pursuer policy depends on two key factors: the balance of diversity and optimality of the evader's behavior and the strength of the modeling assumptions in the fully-observable policy. We deploy our policy on a physical quadruped robot with an RGB-D camera on pursuit-evasion interactions in the wild. Despite all the challenges, the sensing constraints bring about creativity: the robot is pushed to gather information when uncertain, predict intent from noisy measurements, and anticipate in order to intercept. Project webpage: https://abajcsy.github.io/vision-based-pursuit/