Model-Based Relative Entropy Stochastic Search

Authors: Abbas Abdolmaleki, Rudolf Lioutikov, Jan R. Peters, Nuno Lau, Luis Pualo Reis, Gerhard Neumann

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We compare our method with state of art black-box optimization methods on standard uni-modal and multi-modal optimization functions, on simulated planar robot tasks and a complex robot ball throwing task. The proposed method considerably outperforms the existing approaches.
Researcher Affiliation Academia 1: IEETA, University of Aveiro, Aveiro, Portugal 2: DSI, University of Minho, Braga, Portugal 3: LIACC, University of Porto, Porto, Portugal 4: IAS, 5: CLAS, TU Darmstadt, Darmstadt, Germany 6: Max Planck Institute for Intelligent Systems, Stuttgart, Germany
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper uses standard optimization test functions (Rosenbrock, Rastrigin) and simulated robot tasks, but does not provide concrete access information (link, DOI, specific citation) for a publicly available or open dataset.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for training, validation, or testing.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, processor types, memory amounts) used for running its experiments.
Software Dependencies No The paper mentions software components and algorithms used (e.g., DMPs, CMA-ES, NES, REPS) but does not provide specific version numbers for any of them.
Experiment Setup Yes In each iteration, we generated 15 new samples. For MORE, REPS and Po WER, we always keep the last L = 150 samples... We used 5 basis functions per degree of freedom for the DMPs... We generated 40 new samples. For MORE, REPS, we always keep the last L = 200 samples.