Maximum Total Correlation Reinforcement Learning

• URL: http://arxiv.org/abs/2505.16734v1
• Date: Thu, 22 May 2025 14:48:00 GMT
• Title: Maximum Total Correlation Reinforcement Learning
• Authors: Bang You, Puze Liu, Huaping Liu, Jan Peters, Oleg Arenz,
• Abstract summary: We introduce a modification of the reinforcement learning problem that additionally maximizes the total correlation within the induced trajectories.<n>In simulated robot environments, our method naturally generates policies that induce periodic and compressible trajectories.
• Score: 23.209609715886454
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Simplicity is a powerful inductive bias. In reinforcement learning, regularization is used for simpler policies, data augmentation for simpler representations, and sparse reward functions for simpler objectives, all that, with the underlying motivation to increase generalizability and robustness by focusing on the essentials. Supplementary to these techniques, we investigate how to promote simple behavior throughout the episode. To that end, we introduce a modification of the reinforcement learning problem that additionally maximizes the total correlation within the induced trajectories. We propose a practical algorithm that optimizes all models, including policy and state representation, based on a lower-bound approximation. In simulated robot environments, our method naturally generates policies that induce periodic and compressible trajectories, and that exhibit superior robustness to noise and changes in dynamics compared to baseline methods, while also improving performance in the original tasks.

Related papers

• Relative Entropy Pathwise Policy Optimization [56.86405621176669]
  We show how to construct a value-gradient driven, on-policy algorithm that allow training Q-value models purely from on-policy data.<n>We propose Relative Entropy Pathwise Policy Optimization (REPPO), an efficient on-policy algorithm that combines the sample-efficiency of pathwise policy gradients with the simplicity and minimal memory footprint of standard on-policy learning.
  arXiv  Detail & Related papers  (2025-07-15T06:24:07Z)
• Diffusion Guidance Is a Controllable Policy Improvement Operator [98.11511661904618]
  CFGRL is trained with the simplicity of supervised learning, yet can further improve on the policies in the data.<n>On offline RL tasks, we observe a reliable trend -- increased guidance weighting leads to increased performance.
  arXiv  Detail & Related papers  (2025-05-29T14:06:50Z)
• Trajectory Entropy Reinforcement Learning for Predictable and Robust Control [12.289021814766539]
  We introduce a novel inductive bias towards simple policies in reinforcement learning.<n>The simplicity inductive bias is introduced by minimizing the entropy of entire action trajectories.<n>We show that our learned policies produce more cyclical and consistent action trajectories.
  arXiv  Detail & Related papers  (2025-05-07T07:41:29Z)
• Salience-Invariant Consistent Policy Learning for Generalization in Visual Reinforcement Learning [12.9372563969007]
  Generalizing policies to unseen scenarios remains a critical challenge in visual reinforcement learning.<n>In unseen environments, distracting pixels may lead agents to extract representations containing task-irrelevant information.<n>We propose the Salience-Invariant Consistent Policy Learning algorithm, an efficient framework for zero-shot generalization.
  arXiv  Detail & Related papers  (2025-02-12T12:00:16Z)
• Improving generalization of robot locomotion policies via Sharpness-Aware Reinforcement Learning [0.5399800035598186]
  Differentiable simulators offer improved sample efficiency through exact gradients, but can be unstable in contact-rich environments.<n>This paper introduces a novel approach integrating sharpness-aware optimization into gradient-based reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2024-11-29T14:25:54Z)
• Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity [51.40558987254471]
  Real-world applications of reinforcement learning often involve environments where agents operate on complex, high-dimensional observations. This paper addresses the question of reinforcement learning under $textitgeneral$ latent dynamics from a statistical and algorithmic perspective.
  arXiv  Detail & Related papers  (2024-10-23T14:22:49Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Learning a Diffusion Model Policy from Rewards via Q-Score Matching [93.0191910132874]
  We present a theoretical framework linking the structure of diffusion model policies to a learned Q-function.<n>We propose a new policy update method from this theory, which we denote Q-score matching.
  arXiv  Detail & Related papers  (2023-12-18T23:31:01Z)
• A Regularized Implicit Policy for Offline Reinforcement Learning [54.7427227775581]
  offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. We propose a framework that supports learning a flexible yet well-regularized fully-implicit policy. Experiments and ablation study on the D4RL dataset validate our framework and the effectiveness of our algorithmic designs.
  arXiv  Detail & Related papers  (2022-02-19T20:22:04Z)
• OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching [12.335788185691916]
  Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious. Prior IRL algorithms use on-policy transitions, which require intensive sampling from the current policy for stable and optimal performance. We present Off-Policy Inverse Reinforcement Learning (OPIRL), which adopts off-policy data distribution instead of on-policy.
  arXiv  Detail & Related papers  (2021-09-09T14:32:26Z)
• Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling [126.69933134648541]
  We present a meta-reinforcement learning algorithm that is both efficient and extrapolates well when faced with out-of-distribution tasks at test time. Our method is based on a simple insight: we recognize that dynamics models can be adapted efficiently and consistently with off-policy data.
  arXiv  Detail & Related papers  (2020-06-12T13:34:46Z)

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.