Data to 7 Oct 2026

An empirical investigation of the challenges of real-world reinforcement learning

arXiv 2003.11881 ↗First posted 24 Mar 2020cs.LG cs.AIcited by 75

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research advances in RL are hard to leverage in real-world systems due to a series of assumptions that are rarely satisfied in practice. In this work, we identify and formalize a series of independent challenges that embody the difficulties that must be addressed for RL to be commonly deployed in real-world systems. For each challenge, we define it formally in the context of a Markov Decision Process, analyze the effects of the challenge on state-of-the-art learning algorithms, and present some existing attempts at tackling it. We believe that an approach that addresses our set of proposed challenges would be readily deployable in a large number of real world problems. Our proposed challenges are implemented in a suite of continuous control environments called the realworldrl-suite which we propose an as an open-source benchmark.

Key facts. Cited by 75 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 2; 2021: 24; 2022: 8; 2023: 17; 2024: 8; 2025: 8; 2026: 8.

75 papers.

Sort:

By area:

2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 501
2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
2022A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problemscited by 228
2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
2021Pretraining Representations for Data-Efficient Reinforcement Learningcited by 105
2021MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Researchcited by 96
2021Learning and Planning in Complex Action Spacescited by 76
2022COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimationcited by 69
2021Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Controlcited by 68
2021NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learningcited by 63
2020RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learningcited by 57
2021RobustNav: Towards Benchmarking Robustness in Embodied Navigationcited by 52

38 more

2022Holo-Dex: Teaching Dexterity with Immersive Mixed Realitycited by 52
2021DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learningcited by 47
2021safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Roboticscited by 42
2021Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policiescited by 37
2021RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learningcited by 31
2021Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systemscited by 24
2023Benchmarking Offline Reinforcement Learning on Real-Robot Hardwarecited by 23
2023Causal Reinforcement Learning: A Surveycited by 22
2022Mastering the Unsupervised Reinforcement Learning Benchmark from Pixelscited by 20
2022Asynchronous Reinforcement Learning for Real-Time Control of Physical Robotscited by 19
2023ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPscited by 19
2021AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learningcited by 17
2025Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategycited by 15
2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
2023Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learningcited by 12
2023A Survey of Demonstration Learningcited by 12
2021Fast and Data-Efficient Training of Rainbow: an Experimental Study on Ataricited by 10
2021Learning to Centralize Dual-Arm Assemblycited by 9
2023Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guaranteescited by 9
2023A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learningcited by 9
2023Novelty Detection in Reinforcement Learning with World Modelscited by 8
2025SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfercited by 8
2020On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstrationcited by 6
2022SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Criticscited by 6
2023Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernelcited by 6
2023ContainerGym: A Real-World Reinforcement Learning Benchmark for Resource Allocationcited by 6
2026Safe Exploration via Policy Priorscited by 6
2023An Invitation to Deep Reinforcement Learningcited by 5
2025Reinforcement learning with combinatorial actions for coupled restless banditscited by 5
2023Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithmscited by 4
2025HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agentscited by 4
2021Offline Policy Comparison under Limited Historical Agent-Environment Interactionscited by 3
2022Sim2real for Reinforcement Learning Driven Next Generation Networkscited by 3
2023Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real Worldcited by 3
2021Learning-based vs Model-free Adaptive Control of a MAV under Wind Gustcited by 2
2021GrowSpace: Learning How to Shape Plantscited by 2
2021Towards Interactive Reinforcement Learning with Intrinsic Feedbackcited by 2
2022K-nearest Multi-agent Deep Reinforcement Learning for Collaborative Tasks with a Variable Number of Agentscited by 2

50 most cited of 75 All 75 (JSON)