Prioritized Generative Replay

• URL: http://arxiv.org/abs/2410.18082v1
• Date: Wed, 23 Oct 2024 17:59:52 GMT
• Title: Prioritized Generative Replay
• Authors: Renhao Wang, Kevin Frans, Pieter Abbeel, Sergey Levine, Alexei A. Efros,
• Abstract summary: We propose a prioritized, parametric version of an agent's memory, using generative models to capture online experience. This paradigm enables densification of past experience, with new generations that benefit from the generative model's generalization capacity. We show this recipe can be instantiated using conditional diffusion models and simple relevance functions.
• Score: 121.83947140497655
• License:
• Abstract: Sample-efficient online reinforcement learning often uses replay buffers to store experience for reuse when updating the value function. However, uniform replay is inefficient, since certain classes of transitions can be more relevant to learning. While prioritization of more useful samples is helpful, this strategy can also lead to overfitting, as useful samples are likely to be more rare. In this work, we instead propose a prioritized, parametric version of an agent's memory, using generative models to capture online experience. This paradigm enables (1) densification of past experience, with new generations that benefit from the generative model's generalization capacity and (2) guidance via a family of "relevance functions" that push these generations towards more useful parts of an agent's acquired history. We show this recipe can be instantiated using conditional diffusion models and simple relevance functions such as curiosity- or value-based metrics. Our approach consistently improves performance and sample efficiency in both state- and pixel-based domains. We expose the mechanisms underlying these gains, showing how guidance promotes diversity in our generated transitions and reduces overfitting. We also showcase how our approach can train policies with even higher update-to-data ratios than before, opening up avenues to better scale online RL agents.

Related papers

• 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)
• Class incremental learning with probability dampening and cascaded gated classifier [4.285597067389559]
  We propose a novel incremental regularisation approach called Margin Dampening and Cascaded Scaling. The first combines a soft constraint and a knowledge distillation approach to preserve past knowledge while allowing forgetting new patterns. We empirically show that our approach performs well on multiple benchmarks well-established baselines.
  arXiv  Detail & Related papers  (2024-02-02T09:33:07Z)
• Continual Learning with Strong Experience Replay [32.154995019080594]
  We propose a CL method with Strong Experience Replay (SER) SER utilizes future experiences mimicked on the current training data, besides distilling past experience from the memory buffer. Experimental results on multiple image classification datasets show that our SER method surpasses the state-of-the-art methods by a noticeable margin.
  arXiv  Detail & Related papers  (2023-05-23T02:42:54Z)
• Understanding the effect of varying amounts of replay per step [0.0]
  We study the effect of varying amounts of replay per step in a well-known model-free algorithm: Deep Q-Network (DQN) in the Mountain Car environment.
  arXiv  Detail & Related papers  (2023-02-20T20:54:11Z)
• A Memory Transformer Network for Incremental Learning [64.0410375349852]
  We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to class-incremental learning results in the "catastrophic forgetting" of previously seen classes. One of the most successful existing methods has been the use of a memory of exemplars, which overcomes the issue of catastrophic forgetting by saving a subset of past data into a memory bank and utilizing it to prevent forgetting when training future tasks.
  arXiv  Detail & Related papers  (2022-10-10T08:27:28Z)
• SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning [168.89470249446023]
  We present SURF, a semi-supervised reward learning framework that utilizes a large amount of unlabeled samples with data augmentation. In order to leverage unlabeled samples for reward learning, we infer pseudo-labels of the unlabeled samples based on the confidence of the preference predictor. Our experiments demonstrate that our approach significantly improves the feedback-efficiency of the preference-based method on a variety of locomotion and robotic manipulation tasks.
  arXiv  Detail & Related papers  (2022-03-18T16:50:38Z)
• Reducing Representation Drift in Online Continual Learning [87.71558506591937]
  We study the online continual learning paradigm, where agents must learn from a changing distribution with constrained memory and compute. In this work we instead focus on the change in representations of previously observed data due to the introduction of previously unobserved class samples in the incoming data stream.
  arXiv  Detail & Related papers  (2021-04-11T15:19:30Z)
• Learning to Sample with Local and Global Contexts in Experience Replay Buffer [135.94190624087355]
  We propose a new learning-based sampling method that can compute the relative importance of transition. We show that our framework can significantly improve the performance of various off-policy reinforcement learning methods.
  arXiv  Detail & Related papers  (2020-07-14T21:12:56Z)
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
  Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
  arXiv  Detail & Related papers  (2020-06-22T15:07:06Z)

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.