Adaptive Data Exploitation in Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2501.12620v1
• Date: Wed, 22 Jan 2025 04:01:17 GMT
• Title: Adaptive Data Exploitation in Deep Reinforcement Learning
• Authors: Mingqi Yuan, Bo Li, Xin Jin, Wenjun Zeng,
• Abstract summary: We introduce ADEPT, a powerful framework to enhance the **data efficiency** and **generalization** in deep reinforcement learning (RL) Specifically, ADEPT adaptively manages the use of sampled data across different learning stages via multi-armed bandit (MAB) algorithms. We test ADEPT on benchmarks including Procgen, MiniGrid, and PyBullet.
• Score: 50.53705050673944
• License:
• Abstract: We introduce ADEPT: Adaptive Data ExPloiTation, a simple yet powerful framework to enhance the **data efficiency** and **generalization** in deep reinforcement learning (RL). Specifically, ADEPT adaptively manages the use of sampled data across different learning stages via multi-armed bandit (MAB) algorithms, optimizing data utilization while mitigating overfitting. Moreover, ADEPT can significantly reduce the computational overhead and accelerate a wide range of RL algorithms. We test ADEPT on benchmarks including Procgen, MiniGrid, and PyBullet. Extensive simulation demonstrates that ADEPT can achieve superior performance with remarkable computational efficiency, offering a practical solution to data-efficient RL. Our code is available at https://github.com/yuanmingqi/ADEPT.

Related papers

• Optimizing Pretraining Data Mixtures with LLM-Estimated Utility [52.08428597962423]
  Large Language Models improve with increasing amounts of high-quality training data. We find token-counts outperform manual and learned mixes, indicating that simple approaches for dataset size and diversity are surprisingly effective. We propose two complementary approaches: UtiliMax, which extends token-based $200s by incorporating utility estimates from reduced-scale ablations, achieving up to a 10.6x speedup over manual baselines; and Model Estimated Data Utility (MEDU), which leverages LLMs to estimate data utility from small samples, matching ablation-based performance while reducing computational requirements by $simx.
  arXiv  Detail & Related papers  (2025-01-20T21:10:22Z)
• Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws [59.03420759554073]
  We introduce Adaptive Data Optimization (ADO), an algorithm that optimize data distributions in an online fashion, concurrent with model training. ADO does not require external knowledge, proxy models, or modifications to the model update. ADO uses per-domain scaling laws to estimate the learning potential of each domain during training and adjusts the data mixture accordingly.
  arXiv  Detail & Related papers  (2024-10-15T17:47:44Z)
• CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMs [30.441431693349866]
  Existing methods generate vast amounts of synthetic data for fine-tuning, leading to inefficiencies in training. CodeACT introduces the Complexity and Diversity Aware Sampling (CDAS) method to select high-quality training data. CodeACT achieves an 8.6% performance increase on HumanEval, reduces training time by 78%, and decreases peak GPU memory usage by 27%.
  arXiv  Detail & Related papers  (2024-08-05T02:38:48Z)
• Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning [55.96599486604344]
  We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process. We use Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals. The proposed algorithm employs Direct Preference Optimization (DPO) to update the LLM policy using this newly generated step-level preference data.
  arXiv  Detail & Related papers  (2024-05-01T11:10:24Z)
• Enhancing data efficiency in reinforcement learning: a novel imagination mechanism based on mesh information propagation [0.3729614006275886]
  We introduce a novel mesh information propagation mechanism, termed the 'Imagination Mechanism (IM)' IM enables information generated by a single sample to be effectively broadcasted to different states across episodes. To promote versatility, we extend the IM to function as a plug-and-play module that can be seamlessly and fluidly integrated into other widely adopted RL algorithms.
  arXiv  Detail & Related papers  (2023-09-25T16:03:08Z)
• Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity [8.068886870457561]
  Deep Reinforcement Learning (DRL) has exhibited efficacy in resolving the Local Path Planning (LPP) problem. Such application in the real world is immensely limited due to the deficient training efficiency and generalization capability of DRL. A solution named Color is proposed, which consists of an Actor-Sharer-Learner (ASL) training framework and a mobile robot-oriented simulator Sparrow.
  arXiv  Detail & Related papers  (2023-05-07T03:39:31Z)
• Efficient Online Reinforcement Learning with Offline Data [78.92501185886569]
  We show that we can simply apply existing off-policy methods to leverage offline data when learning online. We extensively ablate these design choices, demonstrating the key factors that most affect performance. We see that correct application of these simple recommendations can provide a $mathbf2.5times$ improvement over existing approaches.
  arXiv  Detail & Related papers  (2023-02-06T17:30:22Z)
• A Distributed Deep Reinforcement Learning Technique for Application Placement in Edge and Fog Computing Environments [31.326505188936746]
  Several Deep Reinforcement Learning (DRL)-based placement techniques have been proposed in fog/edge computing environments. We propose an actor-critic-based distributed application placement technique, working based on the IMPortance weighted Actor-Learner Architectures (IMPALA)
  arXiv  Detail & Related papers  (2021-10-24T11:25:03Z)
• AWAC: Accelerating Online Reinforcement Learning with Offline Datasets [84.94748183816547]
  We show that our method, advantage weighted actor critic (AWAC), enables rapid learning of skills with a combination of prior demonstration data and online experience. Our results show that incorporating prior data can reduce the time required to learn a range of robotic skills to practical time-scales.
  arXiv  Detail & Related papers  (2020-06-16T17:54:41Z)

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.