mlsanityData to 7 Oct 2026

Evolving Rewards to Automate Reinforcement Learning

arXiv 1905.07628 ↗First posted 18 May 2019cs.LG cs.AI cs.NEcited by 28

Not on the map. Why?

Abstract (arXiv)

Many continuous control tasks have easily formulated objectives, yet using them directly as a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many classical control tasks guide RL training using complex rewards, which require tedious hand-tuning. We automate the reward search with AutoRL, an evolutionary layer over standard RL that treats reward tuning as hyperparameter optimization and trains a population of RL agents to find a reward that maximizes the task objective. AutoRL, evaluated on four Mujoco continuous control tasks over two RL algorithms, shows improvements over baselines, with the the biggest uplift for more complex tasks. The video can be found at: urlhttps://youtu.be/svdaOFfQyC8.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 8; 2023: 7; 2024: 5; 2025: 3; 2026: 1.

28 papers.

Sort:

By area:

  1. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  2. 2023Preference Transformer: Modeling Human Preferences using Transformers for RLcited by 77
  3. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  4. 2023Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraftcited by 60
  5. 2021Evolving Reinforcement Learning Algorithmscited by 48
  6. 2023Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Roboticscited by 35
  7. 2023Evolutionary Reinforcement Learning: A Surveycited by 24
  8. 2022Open Source Vizier: Distributed Infrastructure and API for Reliable and Flexible Blackbox Optimizationcited by 17
  9. 2023AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learningcited by 16
  10. 2022TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learningcited by 15
  11. 2022Reinforcement Learning with Automated Auxiliary Loss Searchcited by 12
  12. 2022Automated Reinforcement Learning: An Overviewcited by 9
16 more
  1. 2022Learning Synthetic Environments and Reward Networks for Reinforcement Learningcited by 6
  2. 2024Combining Automated Optimisation of Hyperparameters and Reward Shapecited by 5
  3. 2021Learning Robotic Manipulation Skills Using an Adaptive Force-Impedance Action Spacecited by 4
  4. 2025RoboMoRe: LLM-based Robot Co-design via Joint Optimization of Morphology and Rewardcited by 4
  5. 2023Deep Reinforcement Learning from Hierarchical Preference Designcited by 3
  6. 2024Discovering Minimal Reinforcement Learning Environmentscited by 3
  7. 2021Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific researchcited by 1
  8. 2022Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stabilitycited by 1
  9. 2024Continuously evolving rewards in an open-ended environmentcited by 1
  10. 2025An Automated Reinforcement Learning Reward Design Framework with Large Language Model for Cooperative Platoon Coordinationcited by 1
  11. 2026RDA: Reward Design Agent for Reinforcement Learningcited by 1
  12. 2021A model-based framework for learning transparent swarm behaviorscited by 0
  13. 2022Robot Navigation Anticipative Strategies in Deep Reinforcement Motion Planningcited by 0
  14. 2024mathrmE2CFD: Towards Effective and Efficient Cost Function Design for Safe Reinforcement Learning via Large Language Modelcited by 0
  15. 2024When to Localize? A Risk-Constrained Reinforcement Learning Approachcited by 0
  16. 2025SATA: Safe and Adaptive Torque-Based Locomotion Policies Inspired by Animal Learningcited by 0