Co-imitation: Learning Design and Behaviour by Imitation
Authors: Chang Rajani, Karol Arndt, David Blanco-Mulero, Kevin Sebastian Luck, Ville Kyrki
AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experimental evaluation aims at answering the following research questions: (Q1) Does imitation learning benefit from co-adapting the imitator s morphology? (Q2) How does the choice of the imitation learning algorithm used with Co IL impact the imitator s morphology? (Q3) Is morphology adaptation with Co IL able to compensate for major morphology differences, such as a missing joint or the transfer from a real to a simulated agent? To answer these questions, we devised a set of experiments across a range of setups and imitation learning methods. |
| Researcher Affiliation | Academia | 1Department of Computer Science, University of Helsinki, Finland, 2Department of Electrical Engineering and Automation (EEA), Aalto University, Finland, 3Finnish Center for Artificial Intelligence, Finland |
| Pseudocode | Yes | An overview of Co IL is provided in Algorithm 1. ... Algorithm 1: Co-Imitation Learning (Co IL) ... Algorithm 2: Bayesian Morphology Optimization |
| Open Source Code | No | The paper provides a link to videos related to the project ('Find videos at https://sites.google.com/view/co-imitation'), but it does not contain an explicit statement or a link to the open-source code for the methodology described. |
| Open Datasets | Yes | Here, we use a Humanoid robot adapted from Open AI Gym (Brockman et al. 2016) together with the CMU motion capture data (CMU 2019) as our demonstrations. ... CMU. 2019. CMU Graphics Lab Motion Capture Database. http://mocap.cs.cmu.edu/. Accessed: 2022-08-01. |
| Dataset Splits | No | The paper states that it uses 'demonstration datasets' and 'expert trajectories' (e.g., from CMU motion capture data), but it does not provide specific information about training, validation, or test dataset splits, such as percentages, sample counts, or a detailed splitting methodology. |
| Hardware Specification | No | The paper mentions 'computational resources provided by the Aalto Science-IT project' but does not provide specific details such as exact GPU/CPU models, processor types, or memory amounts used for running the experiments. |
| Software Dependencies | No | The paper mentions software components like 'Mu Jo Co physics engine', 'Open AI Gym', and 'pot package', but it does not provide specific version numbers for these or any other ancillary software used in the experiments. |
| Experiment Setup | Yes | As discussed in Algorithm 1, the policies are trained using the same morphology for Nξ = 20 episodes. ... We optimize morphological parameters such as the lengths of arms and legs, and diameter of torso elements in humanoid (see also Table 6, Appendix). ... α( ξ) = µ( ξ) βσ( ξ), where β (here 2) is a parameter that controls the exploration. |