Continuous-time Model-based Reinforcement Learning

Authors: Cagatay Yildiz, Markus Heinonen, Harri Lähdesmäki

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We implement and test our method on a new ODE-RL suite that explicitly solves continuous-time control systems. Our experiments illustrate that the model is robust against irregular and noisy data, is sampleefficient, and can solve control problems which pose challenges to discrete-time MBRL methods.
Researcher Affiliation Academia 1Department of Computer Science, Aalto University, Finland.
Pseudocode Yes Algorithm 1 Continuous-Time MBRL with Neural ODEs
Open Source Code Yes Our model implementation can be found at https://github.com/cagatayyildiz/oderl
Open Datasets Yes The test environments are already implemented in standard RL frameworks such as Open AI Gym (Brockman et al., 2016) and Deep Mind Control Suite (Tassa et al., 2018).
Dataset Splits No The paper mentions "train and test one-step ahead prediction errors" but does not specify explicit validation splits (e.g., percentages or counts) or refer to a standard validation methodology.
Hardware Specification No The paper does not provide specific details about the hardware used for experiments, such as GPU or CPU models, memory, or specific cloud instance types.
Software Dependencies No The paper states "We implement our method in Py Torch (Paszke et al., 2019)" but does not specify the version number of PyTorch or any other software dependencies.
Experiment Setup Yes In the remainder of this paper, we fix H = 2.0 and nens = 10.