Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes

Authors: Mengdi Xu, Wenhao Ding, Jiacheng Zhu, ZUXIN LIU, Baiming Chen, Ding Zhao

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In experiments, our approach outperforms alternative methods in non-stationary tasks, including classic control with changing dynamics and decision making in different driving scenarios.
Researcher Affiliation Academia Carnegie Mellon University {mengdixu, wenhaod, jzhu4, zuxinl, baimingc, dingzhao}@andrew.cmu.edu
Pseudocode Yes Algorithm 1: Bayesian Inference for Continual Online Model-based Reinforcement Learning
Open Source Code Yes Codes available at: https://github.com/mxu34/mbrl-gpmm.
Open Datasets No The paper mentions using environments like 'Cartpole-Swing Up, Half Cheetah and Highway Intersection', but does not provide concrete access information (link, DOI, citation) to specific datasets used for training, validation, or testing.
Dataset Splits No The paper does not provide specific percentages or counts for training, validation, or test dataset splits. It describes an online learning setting with streaming data.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments (e.g., GPU/CPU models, memory).
Software Dependencies No The paper does not provide specific version numbers for any software dependencies or libraries used in the experiments.
Experiment Setup No The paper does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size) or detailed training configurations in the main text.