mlsanityData to 7 Oct 2026

ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders

arXiv 2605.19503 ↗First posted 19 May 2026cs.RO cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning for legged locomotion has matured into a stack of multi-component reward functions and physics-engine benchmarks whose morphologies are uniformly derived from real commercial hardware. Game NPCs, however, are bound by stylistic constraints absent from sim-to-real robotics and routinely take the form of creatures with no real-robot counterpart. We introduce ARC-RL, a suite of four MuJoCo continuous-control environments featuring robotic morphologies inspired by the bestiary of ARC Raiders: the 18-DoF tall hexapod Queen, the 12-DoF armoured hexapod Bastion, the 18-DoF compact hexapod Tick, and the 12-DoF quadruped Leaper. All four robots share a unified observation template, action convention, simulation cadence, and a single closed-form multi-component reward function whose only per-morphology variation lives in a small set of weights and parameters. The reward fuses a velocity-tracking tent, a healthy survive bonus, a phase-locked gait-compliance bonus/cost pair, action regularisers, three safety penalties, and a posture anchor; no motion-capture data enters the reward at any point. We additionally provide hand-crafted Central Pattern Generator demonstrators per morphology, which serve both as fixed expert references and as sources of prior data for offline-to-online training. On this playground, we conduct a controlled empirical study comparing standard online algorithms (SAC, SPEQ, SOPE-EO) and methods augmented with prior data (SACfD, SPEQ-O2O, SOPE), and characterise how each paradigm copes with the playground's morphological diversity and animation-style stylistic constraints. Source code is available at https://github.com/CarloRomeo427/ARC_RL.git.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 51 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

31 of 51 references.

References · 31

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  3. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  4. 2018DeepMind Control Suitecited by 935
  5. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  6. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  7. 2019Learning agile and dynamic motor skills for legged robotscited by 402
  8. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 395
  9. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 375
  10. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
  11. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 299
  12. 2018Unity: A General Platform for Intelligent Agentscited by 232
19 more
  1. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 229
  2. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 193
  3. 2023Extreme Parkour with Legged Robotscited by 120
  4. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 113
  5. 2021Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learningcited by 73
  6. 2020Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Compositioncited by 71
  7. 2024Scaling Instructable Agents Across Many Simulated Worldscited by 67
  8. 2019Policies Modulating Trajectory Generatorscited by 47
  9. 2020Regularizing Action Policies for Smooth Control with Reinforcement Learningcited by 47
  10. 2018Feedback Control For Cassie With Deep Reinforcement Learningcited by 36
  11. 2023Barkour: Benchmarking Animal-level Agility with Quadruped Robotscited by 33
  12. 2022CPG-RL: Learning Central Pattern Generators for Quadruped Locomotioncited by 24
  13. 2022Learning Free Gait Transition for Quadruped Robots via Phase-Guided Controllercited by 23
  14. 2023ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robotscited by 15
  15. 2022Towards Informed Design and Validation Assistance in Computer Games Using Imitation Learningcited by 13
  16. 2022Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotioncited by 11
  17. 2025SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learningcited by 7
  18. 2023SYNLOCO: Synthesizing Central Pattern Generator and Reinforcement Learning for Quadruped Locomotioncited by 3
  19. 2026SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Datacited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Manipulator as a Tail: Promoting Dynamic Stability for Legged Locomotion
  2. 2025RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL
  3. 2025Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusion
  4. 2026Learning Highly Dynamic Skills Transition for Quadruped Jumping Through Constrained Space ↗
  5. 2023A Real-World Quadrupedal Locomotion Benchmark for Offline Reinforcement Learning
  6. 2026Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL
  7. 2024Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks
  8. 2025STRIDE: Automating Reward Design, Deep Reinforcement Learning Training and Feedback Optimization in Humanoid Robotics Locomotion