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

• URL: http://arxiv.org/abs/2205.13703v1
• Date: Fri, 27 May 2022 01:30:12 GMT
• Title: Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters
• Authors: Seyed Kamyar Seyed Ghasemipour, Shixiang Shane Gu, Ofir Nachum
• Abstract summary: 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 propose MSG, a practical offline RL algorithm that trains an ensemble of $Q$-functions with independently computed targets based on completely separate networks. Our experiments on the popular D4RL and RL Unplugged offline RL benchmarks demonstrate that MSG with deep ensembles surpasses highly well-tuned state-of-the-art methods by a wide margin.
• Score: 35.17151863463472
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Online Training and Pruning of Deep Reinforcement Learning Networks [0.0]
  Scaling deep neural networks (NN) of reinforcement learning (RL) algorithms has been shown to enhance performance when feature extraction networks are used.<n>We propose an approach to integrate simultaneous training and pruning within advanced RL methods.
  arXiv  Detail & Related papers  (2025-07-16T07:17:41Z)
• Unsupervised Data Generation for Offline Reinforcement Learning: A Perspective from Model [57.20064815347607]
  offline reinforcement learning (RL) recently gains growing interests from RL researchers.<n>The performance of offline RL suffers from the out-of-distribution problem, which can be corrected by feedback in online RL.<n>In this paper, we first build a bridge over the batch data and the performance of offline RL algorithms theoretically.<n>We show that in task-agnostic settings, a series of policies trained by unsupervised RL can minimize the worst-case regret in the performance gap.
  arXiv  Detail & Related papers  (2025-06-24T14:08:36Z)
• NDCG-Consistent Softmax Approximation with Accelerated Convergence [67.10365329542365]
  We propose novel loss formulations that align directly with ranking metrics.<n>We integrate the proposed RG losses with the highly efficient Alternating Least Squares (ALS) optimization method.<n> Empirical evaluations on real-world datasets demonstrate that our approach achieves comparable or superior ranking performance.
  arXiv  Detail & Related papers  (2025-06-11T06:59:17Z)
• DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management [18.953750405635393]
  Decoupled Group Reward Optimization (DGRO) is a general RL algorithm for Large Language Models (LLMs) reasoning.<n>We show that DGRO achieves state-of-the-art performance on the Logic dataset with an average accuracy of 96.9%, and demonstrates strong generalization across mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-05-19T10:44:49Z)
• VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment [66.80143024475635]
  We propose VinePPO, a straightforward approach to compute unbiased Monte Carlo-based estimates. We show that VinePPO consistently outperforms PPO and other RL-free baselines across MATH and GSM8K datasets.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning [39.090104460303415]
  offline model-based reinforcement learning (MBRL) enhances data efficiency by utilizing pre-collected datasets to learn models and policies.<n>This paper first identifies the primary source of this mismatch comes from the underlying confounders present in offline data.<n>We introduce textbfBilintextbfEar textbfCAUSal rtextbfEpresentation(BECAUSE), an algorithm to capture causal representation for both states.
  arXiv  Detail & Related papers  (2024-07-15T17:59:23Z)
• UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning [10.593924216046977]
  We first theoretically analyze overestimation phenomenon led by MSE and provide the theoretical upper bound of the overestimated error. At last, we propose the offline RL algorithm based on underestimated operator and diffusion policy model.
  arXiv  Detail & Related papers  (2024-06-05T14:37:42Z)
• LoRA-Ensemble: Efficient Uncertainty Modelling for Self-attention Networks [52.46420522934253]
  We introduce LoRA-Ensemble, a parameter-efficient deep ensemble method for self-attention networks. By employing a single pre-trained self-attention network with weights shared across all members, we train member-specific low-rank matrices for the attention projections. Our method exhibits superior calibration compared to explicit ensembles and achieves similar or better accuracy across various prediction tasks and datasets.
  arXiv  Detail & Related papers  (2024-05-23T11:10:32Z)
• Stochastic Q-learning for Large Discrete Action Spaces [79.1700188160944]
  In complex environments with discrete action spaces, effective decision-making is critical in reinforcement learning (RL) We present value-based RL approaches which, as opposed to optimizing over the entire set of $n$ actions, only consider a variable set of actions, possibly as small as $mathcalO(log(n)$)$. The presented value-based RL methods include, among others, Q-learning, StochDQN, StochDDQN, all of which integrate this approach for both value-function updates and action selection.
  arXiv  Detail & Related papers  (2024-05-16T17:58:44Z)
• Neural Network Approximation for Pessimistic Offline Reinforcement Learning [17.756108291816908]
  We present a non-asymptotic estimation error of pessimistic offline RL using general neural network approximation. Our result shows that the estimation error consists of two parts: the first converges to zero at a desired rate on the sample size with partially controllable concentrability, and the second becomes negligible if the residual constraint is tight.
  arXiv  Detail & Related papers  (2023-12-19T05:17:27Z)
• SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learning [33.125187822259186]
  Offline Goal-Conditioned Reinforcement Learning (GCRL) is tasked with learning to achieve multiple goals in an environment purely from offline datasets using sparse reward functions. We present a novel approach to GCRL under a new lens of mixture-distribution matching, leading to our discriminator-free method: SMORe.
  arXiv  Detail & Related papers  (2023-11-03T16:19:33Z)
• Provable Reward-Agnostic Preference-Based Reinforcement Learning [61.39541986848391]
  Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories. We propose a theoretical reward-agnostic PbRL framework where exploratory trajectories that enable accurate learning of hidden reward functions are acquired.
  arXiv  Detail & Related papers  (2023-05-29T15:00:09Z)
• Deep Negative Correlation Classification [82.45045814842595]
  Existing deep ensemble methods naively train many different models and then aggregate their predictions. We propose deep negative correlation classification (DNCC) DNCC yields a deep classification ensemble where the individual estimator is both accurate and negatively correlated.
  arXiv  Detail & Related papers  (2022-12-14T07:35:20Z)
• Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning [92.18524491615548]
  Contrastive self-supervised learning has been successfully integrated into the practice of (deep) reinforcement learning (RL) We study how RL can be empowered by contrastive learning in a class of Markov decision processes (MDPs) and Markov games (MGs) with low-rank transitions. Under the online setting, we propose novel upper confidence bound (UCB)-type algorithms that incorporate such a contrastive loss with online RL algorithms for MDPs or MGs.
  arXiv  Detail & Related papers  (2022-07-29T17:29:08Z)
• Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble [16.92791301062903]
  We propose an uncertainty-based offline RL method that takes into account the confidence of the Q-value prediction and does not require any estimation or sampling of the data distribution. Surprisingly, we find that it is possible to substantially outperform existing offline RL methods on various tasks by simply increasing the number of Q-networks along with the clipped Q-learning.
  arXiv  Detail & Related papers  (2021-10-04T16:40:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.