Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios
Authors: Vaisakh Shaj, Dieter Büchler, Rohit Sonker, Philipp Becker, Gerhard Neumann
ICLR 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We show that Hi P-RSSMs outperforms RSSMs and competing multi-task models on several challenging robotic benchmarks both on real-world systems and simulations. and 4 EXPERIMENTS This section evaluates our approach on a diverse set of dynamical systems from the robotics domain in simulations and real systems. |
| Researcher Affiliation | Academia | 1Autonomous Learning Robots, KIT, Germany 2LCAS, University Of Lincoln, UK 3Max Planck Institute for Intelligent Systems, T ubingen, Germany 4Indian Institute Of Technology, Kanpur |
| Pseudocode | Yes | Algorithm 1: Hi P-RSSM Test Time Inference and Algorithm 2: Multi Task Dataset Creation For Training Hi P-RSSM |
| Open Source Code | No | The paper does not contain any explicit statement about making the source code available or a link to a code repository. |
| Open Datasets | No | The paper describes data collected by the authors from various robots and a simulator (Pybullet), but it does not provide concrete access information (e.g., specific links, DOIs, or repositories) for these datasets to be publicly accessed for replication. |
| Dataset Splits | No | The paper specifies training and testing splits for some datasets (e.g., '40 out of the 50 trajectories were used for training and the rest 10 for testing' for the Wheeled Mobile Robot), but it does not explicitly mention or detail a separate validation dataset split. |
| Hardware Specification | No | The paper mentions support from 'bw HPC and the Lichtenberg high performance computer', but it does not provide specific hardware details such as GPU/CPU models, processors, or memory specifications used for running the experiments. |
| Software Dependencies | No | The paper mentions using Pybullet simulator and Adam optimizer, but it does not specify version numbers for these or any other software dependencies, such as PyTorch. |
| Experiment Setup | Yes | The paper provides detailed experimental setup information, including specific hyperparameters like Learning Rate, Latent Observation Dimension, Latent State Dimension, Latent Task Dimension, and architectural details for encoders/decoders in Appendix H. |