# Learning Reach-Avoid Task with Reinforcement Learning: Vectorized Simulation and Benchmark

arXiv: https://arxiv.org/abs/2607.15935 · HTML: https://mlsanity.com/paper/2607.15935/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World](https://mlsanity.com/paper/1709.07643/) (2017)
- [panda-gym: Open-source goal-conditioned environments for robotic learning](https://mlsanity.com/paper/2106.13687/) (2021)
- [Training Larger Networks for Deep Reinforcement Learning](https://mlsanity.com/paper/2102.07920/) (2021)
- [Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods](https://mlsanity.com/paper/1802.10264/) (2018)
- [RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators from RL Policies](https://mlsanity.com/paper/1907.04799/) (2019)
- [Solving Minimum-Cost Reach Avoid using Reinforcement Learning](https://mlsanity.com/paper/2410.22600/) (2024)
- [Accelerating Reinforcement Learning for Reaching using Continuous Curriculum Learning](https://mlsanity.com/paper/2002.02697/) (2020)
- [Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning](https://mlsanity.com/paper/2407.00324/) (2024)
- [The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning](https://mlsanity.com/paper/2210.08607/) (2022)
- [Joint Space Control via Deep Reinforcement Learning](https://mlsanity.com/paper/2011.06332/) (2020)
- [IPPO: Obstacle Avoidance for Robotic Manipulators in Joint Space via Improved Proximal Policy Optimization](https://mlsanity.com/paper/2210.00803/) (2022)
- [Deep-Reinforcement-Learning-based Path Planning for Industrial Robots using Distance Sensors as Observation](https://mlsanity.com/paper/2301.05980/) (2023)

## Abstract (arXiv)

Deep reinforcement learning (DRL) has a longstanding tradition in addressing the reach-avoid task problem, especially for controlling robotic arms. While this task serves as a baseline environment within the research community, the ability of DRL to effectively learn the each-avoid task in complex and realistic scenarios beyond simplified and restricted tabletop settings remains uncertain. In this paper, we present, for the first time, a comprehensive benchmark for the reachavoid task that accurately captures real-world complexities without simplifications. We demonstrate a diverse range of settings for robotic arm reach-avoid task, which can be used for evaluating DRL research. We achieved this by utilizing the MuJoCo MJX physics engine and parallelizing both the simulation environment and DRL algorithms using the Brax library. We achieved state-of-the-art results with success rates of 96.1% (UR5e) and 98.8% (Franka Emika Robot) for the reach task and 86.8% (UR5e) and 95.2% (Franka) for the static reachavoid task. Our results indicate that while in previous works DRL agents could solve, for example, a reach task in a simplified setting perfectly, their agents performance collapses when evaluated in realistic scenarios. Overall, this work identifies that additional research is still required to claim the successful resolution of the robotic arm reach-avoid task using DRL. The environment and benchmarking code is available as open source at the following link