# Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization

arXiv: https://arxiv.org/abs/2311.03351 · HTML: https://mlsanity.com/paper/2311.03351/

## Key facts

- Cited by 26 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 55 of its 61 references that are in the map.
- First posted on arXiv 6 Nov 2023.

## 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 55)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [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)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning](https://mlsanity.com/paper/2208.06193/) (2022)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [COMBO: Conservative Offline Model-Based Policy Optimization](https://mlsanity.com/paper/2102.08363/) (2021)
- [Efficient Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2302.02948/) (2023)
- [Doubly Robust Off-policy Value Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1511.03722/) (2015)
- [Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning](https://mlsanity.com/paper/2303.05479/) (2023)
- [Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble](https://mlsanity.com/paper/2107.00591/) (2021)
- [Online Decision Transformer](https://mlsanity.com/paper/2202.05607/) (2022)
- [RvS: What is Essential for Offline RL via Supervised Learning?](https://mlsanity.com/paper/2112.10751/) (2021)
- [Offline RL Without Off-Policy Evaluation](https://mlsanity.com/paper/2106.08909/) (2021)
- [Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior](https://mlsanity.com/paper/2212.03238/) (2022)
- [Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1911.06854/) (2019)
- [CORL: Research-oriented Deep Offline Reinforcement Learning Library](https://mlsanity.com/paper/2210.07105/) (2022)
- [Extreme Q-Learning: MaxEnt RL without Entropy](https://mlsanity.com/paper/2301.02328/) (2023)
- [Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization](https://mlsanity.com/paper/2303.15810/) (2023)

## Built on by (most cited first, 26 of 26)

- [Diffusion Policy Policy Optimization](https://mlsanity.com/paper/2409.00588/) (2024)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations](https://mlsanity.com/paper/2403.03954/) (2024)
- [RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning](https://mlsanity.com/paper/2510.14830/) (2025)
- [Diffusion Reward: Learning Rewards via Conditional Video Diffusion](https://mlsanity.com/paper/2312.14134/) (2023)
- [World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation](https://mlsanity.com/paper/2509.19080/) (2025)
- [Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning](https://mlsanity.com/paper/2405.20555/) (2024)
- [Learning Visual Quadrupedal Loco-Manipulation from Demonstrations](https://mlsanity.com/paper/2403.20328/) (2024)
- [Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies](https://mlsanity.com/paper/2605.00416/) (2026)
- [Unsupervised-to-Online Reinforcement Learning](https://mlsanity.com/paper/2408.14785/) (2024)
- [Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation](https://mlsanity.com/paper/2601.07821/) (2026)
- [Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL](https://mlsanity.com/paper/2412.18855/) (2024)
- [Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2507.08761/) (2025)
- [Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids](https://mlsanity.com/paper/2508.12252/) (2025)
- [ViTaS: Visual Tactile Soft Fusion Contrastive Learning for Visuomotor Learning](https://mlsanity.com/paper/2602.11643/) (2026)
- [Trust Region Q Adjoint Matching](https://mlsanity.com/paper/2605.27079/) (2026)
- [Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization](https://mlsanity.com/paper/2312.04386/) (2023)
- [Offline Reinforcement Learning with Behavioral Supervisor Tuning](https://mlsanity.com/paper/2404.16399/) (2024)
- [Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration](https://mlsanity.com/paper/2410.19450/) (2024)
- [Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning](https://mlsanity.com/paper/2605.19919/) (2026)
- [SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data](https://mlsanity.com/paper/2605.05863/) (2026)
- [Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network](https://mlsanity.com/paper/2502.00288/) (2025)
- [Online Pre-Training for Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2507.08387/) (2025)
- [Peng's Q(λ) for Conservative Value Estimation in Offline Reinforcement Learning](https://mlsanity.com/paper/2605.14779/) (2026)
- [COOPO: Cyclic Offline-Online Policy Optimization Algorithm](https://mlsanity.com/paper/2605.18675/) (2026)
- [Beyond Safe Execution: Safe Online Reinforcement Learning for Autonomous Driving with Value Calibration and Adaptive Guidance](https://mlsanity.com/paper/2610.17799/) (2026)

## Abstract (arXiv)

Combining offline and online reinforcement learning (RL) is crucial for efficient and safe learning. However, previous approaches treat offline and online learning as separate procedures, resulting in redundant designs and limited performance. We ask: Can we achieve straightforward yet effective offline and online learning without introducing extra conservatism or regularization? In this study, we propose Uni-o4, which utilizes an on-policy objective for both offline and online learning. Owning to the alignment of objectives in two phases, the RL agent can transfer between offline and online learning seamlessly. This property enhances the flexibility of the learning paradigm, allowing for arbitrary combinations of pretraining, fine-tuning, offline, and online learning. In the offline phase, specifically, Uni-o4 leverages diverse ensemble policies to address the mismatch issues between the estimated behavior policy and the offline dataset. Through a simple offline policy evaluation (OPE) approach, Uni-o4 can achieve multi-step policy improvement safely. We demonstrate that by employing the method above, the fusion of these two paradigms can yield superior offline initialization as well as stable and rapid online fine-tuning capabilities. Through real-world robot tasks, we highlight the benefits of this paradigm for rapid deployment in challenging, previously unseen real-world environments. Additionally, through comprehensive evaluations using numerous simulated benchmarks, we substantiate that our method achieves state-of-the-art performance in both offline and offline-to-online fine-tuning learning. Our website: https://lei-kun.github.io/uni-o4/ .