Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay

• URL: http://arxiv.org/abs/2411.10809v1
• Date: Sat, 16 Nov 2024 14:03:23 GMT
• Title: Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay
• Authors: Feng Chen, Fuguang Han, Cong Guan, Lei Yuan, Zhilong Zhang, Yang Yu, Zongzhang Zhang,
• Abstract summary: Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks. This paper introduces a novel continual RL algorithm DISTR that employs a diffusion model to memorize the high-return trajectory distribution of each encountered task. Considering the impracticality of replaying all past data each time, a prioritization mechanism is proposed to prioritize the trajectory replay of pivotal tasks.
• Score: 28.033367285923465
• License:
• Abstract: Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks. Within this problem setting, a pivotal challenge revolves around \textit{catastrophic forgetting} issue, wherein the agent is prone to effortlessly erode the decisional knowledge associated with past encountered tasks when learning the new one. In recent progresses, the \textit{generative replay} methods have showcased substantial potential by employing generative models to replay data distribution of past tasks. Compared to storing the data from past tasks directly, this category of methods circumvents the growing storage overhead and possible data privacy concerns. However, constrained by the expressive capacity of generative models, existing \textit{generative replay} methods face challenges in faithfully reconstructing the data distribution of past tasks, particularly in scenarios with a myriad of tasks or high-dimensional data. Inspired by the success of diffusion models in various generative tasks, this paper introduces a novel continual RL algorithm DISTR (Diffusion-based Trajectory Replay) that employs a diffusion model to memorize the high-return trajectory distribution of each encountered task and wakeups these distributions during the policy learning on new tasks. Besides, considering the impracticality of replaying all past data each time, a prioritization mechanism is proposed to prioritize the trajectory replay of pivotal tasks in our method. Empirical experiments on the popular continual RL benchmark \texttt{Continual World} demonstrate that our proposed method obtains a favorable balance between \textit{stability} and \textit{plasticity}, surpassing various existing continual RL baselines in average success rate.

Related papers

• Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal [54.93261535899478]
  In real-world applications, such as robotic control of reinforcement learning, the tasks are changing, and new tasks arise in a sequential order. This situation poses the new challenge of plasticity-stability trade-off for training an agent who can adapt to task changes and retain acquired knowledge. We propose a rehearsal-based continual diffusion model, called Continual diffuser (CoD), to endow the diffuser with the capabilities of quick adaptation (plasticity) and lasting retention (stability)
  arXiv  Detail & Related papers  (2024-09-04T08:21:47Z)
• State-Space Modeling in Long Sequence Processing: A Survey on Recurrence in the Transformer Era [59.279784235147254]
  This survey provides an in-depth summary of the latest approaches that are based on recurrent models for sequential data processing. The emerging picture suggests that there is room for thinking of novel routes, constituted by learning algorithms which depart from the standard Backpropagation Through Time.
  arXiv  Detail & Related papers  (2024-06-13T12:51:22Z)
• Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay [16.269591842495892]
  We study a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks. We propose a dual generative replay framework that retains previous knowledge by concurrent replay of generated pseudo-data.
  arXiv  Detail & Related papers  (2024-04-16T15:39:11Z)
• t-DGR: A Trajectory-Based Deep Generative Replay Method for Continual Learning in Decision Making [34.02510598090704]
  We propose a simple, scalable, and non-autoregressive method for continual learning in decision-making tasks. We evaluate our method on Continual World benchmarks and find that our approach achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-01-04T23:44:35Z)
• CUDC: A Curiosity-Driven Unsupervised Data Collection Method with Adaptive Temporal Distances for Offline Reinforcement Learning [62.58375643251612]
  We propose a Curiosity-driven Unsupervised Data Collection (CUDC) method to expand feature space using adaptive temporal distances for task-agnostic data collection. With this adaptive reachability mechanism in place, the feature representation can be diversified, and the agent can navigate itself to collect higher-quality data with curiosity. Empirically, CUDC surpasses existing unsupervised methods in efficiency and learning performance in various downstream offline RL tasks of the DeepMind control suite.
  arXiv  Detail & Related papers  (2023-12-19T14:26:23Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning [11.076005074172516]
  reinforcement learning algorithms can easily encounter catastrophic forgetting or interference when faced with lifelong streaming information. We propose a scalable lifelong RL method that dynamically expands the network capacity to accommodate new knowledge. We show that our method successfully facilitates scalable lifelong RL and outperforms relevant existing methods.
  arXiv  Detail & Related papers  (2022-05-22T09:48:41Z)
• Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation [4.111899441919165]
  It is necessary for the model to learn novel relational patterns with very few labeled data while avoiding catastrophic forgetting of previous task knowledge. We propose a novel method based on embedding space regularization and data augmentation. Our method generalizes to new few-shot tasks and avoids catastrophic forgetting of previous tasks by enforcing extra constraints on the relational embeddings and by adding extra relevant data in a self-supervised manner.
  arXiv  Detail & Related papers  (2022-03-04T05:19:09Z)
• Task-agnostic Continual Learning with Hybrid Probabilistic Models [75.01205414507243]
  We propose HCL, a Hybrid generative-discriminative approach to Continual Learning for classification. The flow is used to learn the data distribution, perform classification, identify task changes, and avoid forgetting. We demonstrate the strong performance of HCL on a range of continual learning benchmarks such as split-MNIST, split-CIFAR, and SVHN-MNIST.
  arXiv  Detail & Related papers  (2021-06-24T05:19:26Z)
• Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
  Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. We introduce a new RL formulation for text generation from the soft Q-learning perspective. We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
  arXiv  Detail & Related papers  (2021-06-14T18:48:40Z)
• Posterior Meta-Replay for Continual Learning [4.319932092720977]
  Continual Learning (CL) algorithms have recently received a lot of attention as they attempt to overcome the need to train with an i.i.d. sample from some unknown target data distribution. We study principled ways to tackle the CL problem by adopting a Bayesian perspective and focus on continually learning a task-specific posterior distribution.
  arXiv  Detail & Related papers  (2021-03-01T17:08:35Z)

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.