paper-with-me

Papers

Memory Sequence Length of Data Sampling Impacts the Adaptation of Meta-Reinforcement Learning Agents

2024-06-18 · Menglong Zhang, Fuyuan Qian, Quanying Liu

Fast adaptation to new tasks is extremely important for embodied agents in the real world. Meta-reinforcement learning (meta-RL) has emerged as an effective method to enable fast adaptation in unknown environments. Compared to on-policy meta-RL algorithms, off-policy algorithms rely heavily on efficient data sampling strategies to extract and represent the historical trajectories. However, little is known about how different data sampling methods impact the ability of meta-RL agents to represent unknown environments. Here, we investigate the impact of data sampling strategies on the exploration and adaptability of meta-RL agents. Specifically, we conducted experiments with two types of off-policy meta-RL algorithms based on Thompson sampling and Bayes-optimality theories in continuous control tasks within the MuJoCo environment and sparse reward navigation tasks. Our analysis revealed the long-memory and short-memory sequence sampling strategies affect the representation and adaptive capabilities of meta-RL agents. We found that the algorithm based on Bayes-optimality theory exhibited more robust and better adaptability than the algorithm based on Thompson sampling, highlighting the importance of appropriate data sampling strategies for the agent's representation of an unknown environment, especially in the case of sparse rewards.

📄 PDF Abstract BibTeX arXiv:2406.12359

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous ControlMeta Reinforcement LearningMuJoCoThompson Sampling

Similar Papers 제목 키워드 기반

SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM

2024-06-03 · Quandong Wang, Yuxuan Yuan, Xiaoyu Yang, Ruike Zhang 외

While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-U…

DecoderGPULanguage ModelingLanguage Modelling+1

Using Autoencoders To Learn Interesting Features For Detecting Surveillance Aircraft

2018-09-27 · Teresa Nicole Brooks

This paper explores using a Long short-term memory (LSTM) based sequence autoencoder to learn interesting features for detecting surveillance aircraft using ADS-B flight data. An aircraft periodically broadcasts ADS-B (A…

Time SeriesTime Series Analysis

Demystifying Workload Imbalances in Large Transformer Model Training over Variable-length Sequences

2024-12-10 · Haoyang Li, Fangcheng Fu, Sheng Lin, Hao Ge 외

To optimize large Transformer model training, efficient parallel computing and advanced data management are essential. However, current methods often assume a stable and uniform training workload, neglecting imbalances i…

Management

Assessing the Impact of Sequence Length Learning on Classification Tasks for Transformer Encoder Models

2022-12-16 · Jean-Thomas Baillargeon, Luc Lamontagne

Classification algorithms using Transformer architectures can be affected by the sequence length learning problem whenever observations from different classes have a different length distribution. This problem causes mod…

Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers

2026-05-26 · Kabir Swain, Sijie Han, Daniel Karl I. Weidele, Mauro Martino 외 arxiv

Transformers process images and videos by flattening space and time into long token sequences. While attention and KV caching preserve past features, their memory grows with sequence length and they lack an explicit, per…