Learning Control by Iterative Inversion

Authors: Gal Leibovich, Guy Jacob, Or Avner, Gal Novik, Aviv Tamar

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we evaluate IT-IN on several domains. Our investigation is aimed at studying the unique features of IT-IN and especially, the steering behavior that we expect to observe.
Researcher Affiliation Collaboration 1Intel Labs, Haifa, Israel 2Department of Electrical Engineering, Technion, Haifa, Israel.
Pseudocode Yes Algorithm 1 Iterative Inversion and Algorithm 2 Iterative Inversion for Learning Control
Open Source Code No No explicit statement about releasing the source code for the described methodology or a link to a code repository was found. The provided link (https://sites.google.com/ view/iter-inver) is for videos.
Open Datasets Yes The dataset is from D4RL's hopper-medium-v2 (Fu et al., 2020), and consists of mostly forward hopping behaviors (see Appendix B.3.1).
Dataset Splits Yes When evaluating policies, a validation set of 2,000 trajectories was used, which were unseen during training of the policies.
Hardware Specification No No specific hardware details (GPU/CPU models, memory, etc.) for running the experiments were mentioned.
Software Dependencies No The paper mentions software like "Video GPT (Yan et al., 2021)", "Adam (Kingma & Ba, 2014)", "PPO (Schulman et al., 2017)", and "Kostrikov (2018)" but does not provide specific version numbers for these software components or libraries.
Experiment Setup Yes Table 3 contains a list of common hyperparameter values that we have used for all the experiments. Table 4 contains Particle and Reacher-v2 specific hyperparameters, while Table 5 is listing Hopper-v2 specific hyperparameters.