Extracting Latent State Representations with Linear Dynamics from Rich Observations
Authors: Abraham Frandsen, Rong Ge, Holden Lee
ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We empirically verify our theoretical results with synthetic data and explore the effectiveness of our approach (generalized to nonlinear settings) in simple control tasks with rich observations. |
| Researcher Affiliation | Academia | 1Department of Computer Science, Duke University, Durham, North Carolina, USA 2Department of Mathematics, Duke University, Durham, North Carolina, USA. |
| Pseudocode | No | The paper does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper states: "We implement our learning algorithm in PyTorch (Paszke et al., 2017), and our policy search algorithms use the Stable Baselines library (Hill et al., 2018)." This indicates usage of third-party libraries but does not explicitly state the release of the authors' own source code for the methodology described in this paper. |
| Open Datasets | Yes | We focus on two standard continuous control tasks from Open AI Gym (Brockman et al., 2016): Pendulum-v0 and Mountain Car Continuous-v0. |
| Dataset Splits | No | The paper does not specify explicit training, validation, or test dataset splits (e.g., percentages or sample counts) for the experiments. |
| Hardware Specification | No | The paper does not provide any specific details regarding the hardware used to run the experiments (e.g., GPU/CPU models, memory). |
| Software Dependencies | No | The paper mentions using "PyTorch (Paszke et al., 2017)" and "Stable Baselines library (Hill et al., 2018)" but does not provide specific version numbers for these software dependencies as used in their experiments. |
| Experiment Setup | Yes | For the linear policies, we use all of the default parameters except for the stepsize parameter vf stepsize , which we tested over the range of values [0.00005, 0.0001, 0.0005, 0.001, 0.01, 0.1, 0.5]. |