PILOT: An $\mathcal{O}(1/K)$-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation

Authors: Zhuqing Liu, Xin Zhang, Jia Liu, Zhengyuan Zhu, Songtao Lu

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we conduct our numerical experiments to verify our theoretical results. We compare our work with the basic stochastic gradient (SG) method (Lin et al., 2020b) and three state-of-the-art algorithms for PE: n PD-VR (Wai et al., 2019), STSG (Qiu et al., 2020) and VR-STSG (Qiu et al., 2020). Due to space limitation, we provide our detailed experiment settings in the Appendix. Numerical Results: First, we compare the loss value and gradient norm performance based on Mountain Car-v0 and Cartpole-v0 with n PD-VR, SG, STSG, and VR-STSG in Figs. 1 and 2.
Researcher Affiliation Collaboration Zhuqing Liu , Xin Zhang , Jia Liu , Zhengyuan Zhu , Songtao Lu Department of Electrical and Computer Engineering, The Ohio State University Department of Statistics, Iowa State University IBM Research, IBM Thomas J. Watson Research Center
Pseudocode Yes Algorithm 1: The path-integrated primal-dual stochastic gradient (PILOT)., Algorithm 2: Adaptive-batch PILOT method (PILOT+).
Open Source Code No The paper does not provide a specific repository link or an explicit statement about the release of source code for the described methodology.
Open Datasets Yes Numerical Results: First, we compare the loss value and gradient norm performance based on Mountain Car-v0 and Cartpole-v0 with n PD-VR, SG, STSG, and VR-STSG in Figs. 1 and 2.
Dataset Splits No The paper mentions 'training data' but does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for training, validation, or test sets.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions "OpenAI Gym" but does not provide specific software dependency versions (e.g., library or solver names with version numbers like Python 3.8, PyTorch 1.9, or specific Gym version).
Experiment Setup No Due to space limitation, we provide our detailed experiment settings in the Appendix.