# Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters

arXiv: https://arxiv.org/abs/2205.13703 · HTML: https://mlsanity.com/paper/2205.13703/

## Key facts

- Cited by 76 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 54 of its 78 references that are in the map.
- First posted on arXiv 27 May 2022.

## 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 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [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)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [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)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent](https://mlsanity.com/paper/1902.06720/) (2019)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [Deep Neural Networks as Gaussian Processes](https://mlsanity.com/paper/1711.00165/) (2017)
- [Deep Exploration via Bootstrapped DQN](https://mlsanity.com/paper/1602.04621/) (2016)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [Is Pessimism Provably Efficient for Offline RL?](https://mlsanity.com/paper/2012.15085/) (2020)
- [Gaussian Process Behaviour in Wide Deep Neural Networks](https://mlsanity.com/paper/1804.11271/) (2018)
- [Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble](https://mlsanity.com/paper/2110.01548/) (2021)
- [Critic Regularized Regression](https://mlsanity.com/paper/2006.15134/) (2020)

## Built on by (most cited first, 30 of 76)

- [Supervised Pretraining Can Learn In-Context Reinforcement Learning](https://mlsanity.com/paper/2306.14892/) (2023)
- [Revisiting the Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2305.09836/) (2023)
- [Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning](https://mlsanity.com/paper/2304.01203/) (2023)
- [CORL: Research-oriented Deep Offline Reinforcement Learning Library](https://mlsanity.com/paper/2210.07105/) (2022)
- [Is Value Learning Really the Main Bottleneck in Offline RL?](https://mlsanity.com/paper/2406.09329/) (2024)
- [RORL: Robust Offline Reinforcement Learning via Conservative Smoothing](https://mlsanity.com/paper/2206.02829/) (2022)
- [Offline RL Policies Should be Trained to be Adaptive](https://mlsanity.com/paper/2207.02200/) (2022)
- [Anti-Exploration by Random Network Distillation](https://mlsanity.com/paper/2301.13616/) (2023)
- [A Review of Uncertainty for Deep Reinforcement Learning](https://mlsanity.com/paper/2208.09052/) (2022)
- [Q-learning with Adjoint Matching](https://mlsanity.com/paper/2601.14234/) (2026)
- [What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?](https://mlsanity.com/paper/2305.18882/) (2023)
- [Exploration and Anti-Exploration with Distributional Random Network Distillation](https://mlsanity.com/paper/2401.09750/) (2024)
- [Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning](https://mlsanity.com/paper/2405.20555/) (2024)
- [Corruption-Robust Offline Reinforcement Learning with General Function Approximation](https://mlsanity.com/paper/2310.14550/) (2023)
- [Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning](https://mlsanity.com/paper/2402.03570/) (2024)
- [Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning](https://mlsanity.com/paper/2402.04080/) (2024)
- [Controlling Commercial Cooling Systems Using Reinforcement Learning](https://mlsanity.com/paper/2211.07357/) (2022)
- [Towards Robust Offline Reinforcement Learning under Diverse Data Corruption](https://mlsanity.com/paper/2310.12955/) (2023)
- [Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size](https://mlsanity.com/paper/2211.11092/) (2022)
- [ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles](https://mlsanity.com/paper/2306.06871/) (2023)
- [Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL](https://mlsanity.com/paper/2310.04411/) (2023)
- [Off-Policy Primal-Dual Safe Reinforcement Learning](https://mlsanity.com/paper/2401.14758/) (2024)
- [Offline Multitask Representation Learning for Reinforcement Learning](https://mlsanity.com/paper/2403.11574/) (2024)
- [Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning](https://mlsanity.com/paper/2303.14716/) (2023)
- [Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness](https://mlsanity.com/paper/2309.16973/) (2023)
- [A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective](https://mlsanity.com/paper/2403.07262/) (2024)
- [Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning](https://mlsanity.com/paper/2406.05064/) (2024)
- [Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2302.00521/) (2023)
- [A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2306.07541/) (2023)
- [Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions](https://mlsanity.com/paper/2411.00465/) (2024)

## Abstract (arXiv)

Motivated by the success of ensembles for uncertainty estimation in supervised learning, we take a renewed look at how ensembles of Q-functions can be leveraged as the primary source of pessimism for offline reinforcement learning (RL). We begin by identifying a critical flaw in a popular algorithmic choice used by many ensemble-based RL algorithms, namely the use of shared pessimistic target values when computing each ensemble member's Bellman error. Through theoretical analyses and construction of examples in toy MDPs, we demonstrate that shared pessimistic targets can paradoxically lead to value estimates that are effectively optimistic. Given this result, we propose MSG, a practical offline RL algorithm that trains an ensemble of Q-functions with independently computed targets based on completely separate networks, and optimizes a policy with respect to the lower confidence bound of predicted action values. Our experiments on the popular D4RL and RL Unplugged offline RL benchmarks demonstrate that on challenging domains such as antmazes, MSG with deep ensembles surpasses highly well-tuned state-of-the-art methods by a wide margin. Additionally, through ablations on benchmarks domains, we verify the critical significance of using independently trained Q-functions, and study the role of ensemble size. Finally, as using separate networks per ensemble member can become computationally costly with larger neural network architectures, we investigate whether efficient ensemble approximations developed for supervised learning can be similarly effective, and demonstrate that they do not match the performance and robustness of MSG with separate networks, highlighting the need for new efforts into efficient uncertainty estimation directed at RL.