# SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2007.04938 · HTML: https://mlsanity.com/paper/2007.04938/

## Key facts

- Cited by 152 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2020.

## Built on by (most cited first, 30 of 152)

- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble](https://mlsanity.com/paper/2110.01548/) (2021)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble](https://mlsanity.com/paper/2107.00591/) (2021)
- [Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning](https://mlsanity.com/paper/2202.11566/) (2022)
- [Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?](https://mlsanity.com/paper/2209.03302/) (2022)
- [Dropout Q-Functions for Doubly Efficient Reinforcement Learning](https://mlsanity.com/paper/2110.02034/) (2021)
- [Preference Transformer: Modeling Human Preferences using Transformers for RL](https://mlsanity.com/paper/2303.00957/) (2023)
- [Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters](https://mlsanity.com/paper/2205.13703/) (2022)
- [Reward Uncertainty for Exploration in Preference-based Reinforcement Learning](https://mlsanity.com/paper/2205.12401/) (2022)
- [Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain](https://mlsanity.com/paper/2109.06668/) (2021)
- [VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning](https://mlsanity.com/paper/2202.10324/) (2022)
- [Offline RL Policies Should be Trained to be Adaptive](https://mlsanity.com/paper/2207.02200/) (2022)
- [Randomized Exploration for Reinforcement Learning with General Value Function Approximation](https://mlsanity.com/paper/2106.07841/) (2021)
- [Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning](https://mlsanity.com/paper/2405.20555/) (2024)
- [Thompson sampling for improved exploration in GFlowNets](https://mlsanity.com/paper/2306.17693/) (2023)
- [Ensemble Bootstrapping for Q-Learning](https://mlsanity.com/paper/2103.00445/) (2021)
- [On the Importance of Exploration for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2306.05483/) (2023)
- [Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation](https://mlsanity.com/paper/2201.01666/) (2022)
- [Principled Exploration via Optimistic Bootstrapping and Backward Induction](https://mlsanity.com/paper/2105.06022/) (2021)
- [Regret Minimization Experience Replay in Off-Policy Reinforcement Learning](https://mlsanity.com/paper/2105.07253/) (2021)
- [Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion](https://mlsanity.com/paper/2310.17634/) (2023)
- [Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size](https://mlsanity.com/paper/2211.11092/) (2022)
- [Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL](https://mlsanity.com/paper/2410.20254/) (2024)
- [Confidence-Conditioned Value Functions for Offline Reinforcement Learning](https://mlsanity.com/paper/2212.04607/) (2022)
- [Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration](https://mlsanity.com/paper/2305.18258/) (2023)
- [ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles](https://mlsanity.com/paper/2306.06871/) (2023)
- [Overcoming the Spectral Bias of Neural Value Approximation](https://mlsanity.com/paper/2206.04672/) (2022)
- [Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation](https://mlsanity.com/paper/2107.01825/) (2021)
- [Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning](https://mlsanity.com/paper/2110.03375/) (2021)

## Abstract (arXiv)

Off-policy deep reinforcement learning (RL) has been successful in a range of challenging domains. However, standard off-policy RL algorithms can suffer from several issues, such as instability in Q-learning and balancing exploration and exploitation. To mitigate these issues, we present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy RL algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble, and (b) an inference method that selects actions using the highest upper-confidence bounds for efficient exploration. By enforcing the diversity between agents using Bootstrap with random initialization, we show that these different ideas are largely orthogonal and can be fruitfully integrated, together further improving the performance of existing off-policy RL algorithms, such as Soft Actor-Critic and Rainbow DQN, for both continuous and discrete control tasks on both low-dimensional and high-dimensional environments. Our training code is available at https://github.com/pokaxpoka/sunrise.