UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning

• URL: http://arxiv.org/abs/2406.03324v1
• Date: Wed, 5 Jun 2024 14:37:42 GMT
• Title: UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning
• Authors: Yu Zhang, Rui Yu, Zhipeng Yao, Wenyuan Zhang, Jun Wang, Liming Zhang,
• Abstract summary: 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.
• Score: 10.593924216046977
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Mean Square Error (MSE) is commonly utilized to estimate the solution of the optimal value function in the vast majority of offline reinforcement learning (RL) models and has achieved outstanding performance. However, we find that its principle can lead to overestimation phenomenon for the value function. In this paper, we first theoretically analyze overestimation phenomenon led by MSE and provide the theoretical upper bound of the overestimated error. Furthermore, to address it, we propose a novel Bellman underestimated operator to counteract overestimation phenomenon and then prove its contraction characteristics. At last, we propose the offline RL algorithm based on underestimated operator and diffusion policy model. Extensive experimental results on D4RL tasks show that our method can outperform state-of-the-art offline RL algorithms, which demonstrates that our theoretical analysis and underestimation way are effective for offline RL tasks.

Related papers

• 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)
• Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL [86.0987896274354]
  We first identify a fundamental pattern, self-excitation, as the primary cause of Q-value estimation divergence in offline RL. We then propose a novel Self-Excite Eigenvalue Measure (SEEM) metric to measure the evolving property of Q-network at training. For the first time, our theory can reliably decide whether the training will diverge at an early stage.
  arXiv  Detail & Related papers  (2023-10-06T17:57:44Z)
• 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)
• 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)
• On the Role of Discount Factor in Offline Reinforcement Learning [25.647624787936028]
  The discount factor, $gamma$, plays a vital role in improving online RL sample efficiency and estimation accuracy. This paper examines two distinct effects of $gamma$ in offline RL with theoretical analysis. The results show that the discount factor plays an essential role in the performance of offline RL algorithms.
  arXiv  Detail & Related papers  (2022-06-07T15:22:42Z)
• Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters [35.17151863463472]
  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.
  arXiv  Detail & Related papers  (2022-05-27T01:30:12Z)
• False Correlation Reduction for Offline Reinforcement Learning [115.11954432080749]
  We propose falSe COrrelation REduction (SCORE) for offline RL, a practically effective and theoretically provable algorithm. We empirically show that SCORE achieves the SoTA performance with 3.1x acceleration on various tasks in a standard benchmark (D4RL)
  arXiv  Detail & Related papers  (2021-10-24T15:34:03Z)
• Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL [82.93243616342275]
  We introduce Offline Model-based RL with Adaptive Behavioral Priors (MABE) MABE is based on the finding that dynamics models, which support within-domain generalization, and behavioral priors, which support cross-domain generalization, are complementary. In experiments that require cross-domain generalization, we find that MABE outperforms prior methods.
  arXiv  Detail & Related papers  (2021-06-16T20:48:49Z)
• Instabilities of Offline RL with Pre-Trained Neural Representation [127.89397629569808]
  In offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn) policies in scenarios where the data are collected from a distribution that substantially differs from that of the target policy to be evaluated. Recent theoretical advances have shown that such sample-efficient offline RL is indeed possible provided certain strong representational conditions hold. This work studies these issues from an empirical perspective to gauge how stable offline RL methods are.
  arXiv  Detail & Related papers  (2021-03-08T18:06:44Z)

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.