# NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning

arXiv: https://arxiv.org/abs/2102.00714 · HTML: https://mlsanity.com/paper/2102.00714/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- Placed in Offline RL algorithms, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 36 of its 62 references that are in the map.
- First posted on arXiv 1 Feb 2021.

## Placed in

- Offline RL and imitation learning from data / [Offline RL algorithms](https://mlsanity.com/offlinerl/offline-rl-algorithms/)

## Builds on (most cited first, 30 of 36)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [MOReL : Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2005.05951/) (2020)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [Doubly Robust Off-policy Value Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1511.03722/) (2015)
- [Critic Regularized Regression](https://mlsanity.com/paper/2006.15134/) (2020)
- [Batch Policy Learning under Constraints](https://mlsanity.com/paper/1903.08738/) (2019)
- [Model-Ensemble Trust-Region Policy Optimization](https://mlsanity.com/paper/1802.10592/) (2018)
- [Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning](https://mlsanity.com/paper/2002.08396/) (2020)
- [PLAS: Latent Action Space for Offline Reinforcement Learning](https://mlsanity.com/paper/2011.07213/) (2020)
- [Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1911.06854/) (2019)
- [Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization](https://mlsanity.com/paper/2006.03647/) (2020)
- [Hyperparameter Selection for Offline Reinforcement Learning](https://mlsanity.com/paper/2007.09055/) (2020)
- [Benchmarking Batch Deep Reinforcement Learning Algorithms](https://mlsanity.com/paper/1910.01708/) (2019)
- [BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning](https://mlsanity.com/paper/1910.12179/) (2019)
- [Error Bounds of Imitating Policies and Environments](https://mlsanity.com/paper/2010.11876/) (2020)

## Built on by (most cited first, 30 of 63)

- [A Workflow for Offline Model-Free Robotic Reinforcement Learning](https://mlsanity.com/paper/2109.10813/) (2021)
- [A Survey on Model-based Reinforcement Learning](https://mlsanity.com/paper/2206.09328/) (2022)
- [DiffuserLite: Towards Real-time Diffusion Planning](https://mlsanity.com/paper/2401.15443/) (2024)
- [DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning](https://mlsanity.com/paper/2203.06662/) (2022)
- [Bootstrapped Transformer for Offline Reinforcement Learning](https://mlsanity.com/paper/2206.08569/) (2022)
- [On Transforming Reinforcement Learning by Transformer: The Development Trajectory](https://mlsanity.com/paper/2212.14164/) (2022)
- [Sustainable Online Reinforcement Learning for Auto-bidding](https://mlsanity.com/paper/2210.07006/) (2022)
- [The Generalization Gap in Offline Reinforcement Learning](https://mlsanity.com/paper/2312.05742/) (2023)
- [Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters](https://mlsanity.com/paper/2110.04156/) (2021)
- [Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions](https://mlsanity.com/paper/2402.13777/) (2024)
- [Large Sequence Models for Sequential Decision-Making: A Survey](https://mlsanity.com/paper/2306.13945/) (2023)
- [TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations](https://mlsanity.com/paper/2110.04507/) (2021)
- [Real World Offline Reinforcement Learning with Realistic Data Source](https://mlsanity.com/paper/2210.06479/) (2022)
- [Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning](https://mlsanity.com/paper/2407.00699/) (2024)
- [Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression](https://mlsanity.com/paper/2410.19400/) (2024)
- [Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation](https://mlsanity.com/paper/2109.08331/) (2021)
- [Dungeons and Data: A Large-Scale NetHack Dataset](https://mlsanity.com/paper/2211.00539/) (2022)
- [Dynamic Datasets and Market Environments for Financial Reinforcement Learning](https://mlsanity.com/paper/2304.13174/) (2023)
- [CityLearn v2: Energy-flexible, resilient, occupant-centric, and carbon-aware management of grid-interactive communities](https://mlsanity.com/paper/2405.03848/) (2024)
- [Offline Multi-Objective Optimization](https://mlsanity.com/paper/2406.03722/) (2024)
- [Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation](https://mlsanity.com/paper/2311.18207/) (2023)
- [Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning](https://mlsanity.com/paper/2310.05422/) (2023)
- [D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning](https://mlsanity.com/paper/2408.08441/) (2024)
- [ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning](https://mlsanity.com/paper/2309.03081/) (2023)
- [Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning](https://mlsanity.com/paper/2405.17031/) (2024)
- [Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings](https://mlsanity.com/paper/2112.06127/) (2021)
- [On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective](https://mlsanity.com/paper/2212.12669/) (2022)
- [Exclusively Penalized Q-learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2405.14082/) (2024)
- [Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2407.04285/) (2024)
- [Federated Ensemble-Directed Offline Reinforcement Learning](https://mlsanity.com/paper/2305.03097/) (2023)

## Abstract (arXiv)

Offline reinforcement learning (RL) aims at learning a good policy from a batch of collected data, without extra interactions with the environment during training. However, current offline RL benchmarks commonly have a large reality gap, because they involve large datasets collected by highly exploratory policies, and the trained policy is directly evaluated in the environment. In real-world situations, running a highly exploratory policy is prohibited to ensure system safety, the data is commonly very limited, and a trained policy should be well validated before deployment. In this paper, we present a near real-world offline RL benchmark, named NeoRL, which contains datasets from various domains with controlled sizes, and extra test datasets for policy validation. We evaluate existing offline RL algorithms on NeoRL and argue that the performance of a policy should also be compared with the deterministic version of the behavior policy, instead of the dataset reward. The empirical results demonstrate that the tested offline RL algorithms become less competitive to the deterministic policy on many datasets, and the offline policy evaluation hardly helps. The NeoRL suit can be found at http://polixir.ai/research/neorl. We hope this work will shed some light on future research and draw more attention when deploying RL in real-world systems.