Planning with General Objective Functions: Going Beyond Total Rewards

Authors: Ruosong Wang, Peilin Zhong, Simon S. Du, Russ R. Salakhutdinov, Lin Yang

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This work is mainly theoretical. By devising provably efficient algorithms for planning with general objective functions, we believe our various algorithmic insights (discretization, augmenting state space) could potentially guide practitioners to design efficient and theoretically-principled planning algorithms that work for various settings.
Researcher Affiliation Academia Ruosong Wang Carnegie Mellon University ruosongw@andrew.cmu.edu Peilin Zhong Columbia University pz2225@columbia.edu Simon S. Du University of Washington, Seattle ssdu@cs.washington.edu Ruslan Salakhutdinov Carnegie Mellon University rsalakhu@cs.cmu.edu Lin F. Yang University of California, Los Angeles linyang@ee.ucla.edu
Pseudocode Yes Algorithm 1 Deterministic Systems with General Reward Functions
Open Source Code No The paper does not contain any statement about releasing source code or provide links to a code repository.
Open Datasets No The paper is theoretical and does not conduct experiments on a dataset, hence no mention of publicly available datasets for training.
Dataset Splits No As a theoretical paper, it does not involve data splitting for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not specify software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or training settings.