Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning

Authors: Shenao Zhang

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results also validate the exploration efficiency of CDPO. (Abstract) and 6 Empirical Evaluation (Section 6)
Researcher Affiliation Academia Shenao Zhang Georgia Institute of Technology Atlanta, GA 30332 shenao@gatech.edu
Pseudocode Yes Algorithm 1 Practical CDPO Algorithm
Open Source Code Yes Our code can be found in the supplemental material.
Open Datasets No The paper uses standard RL environments (Mu Jo Co tasks, N-Chain MDPs) for experimentation, but does not provide concrete access information or citations for specific datasets in the way a supervised learning paper would.
Dataset Splits No The paper does not explicitly mention training, validation, or test dataset splits, nor does it provide specific percentages or sample counts for these splits in the provided text.
Hardware Specification No The provided text does not specify any hardware details such as GPU models, CPU types, or cloud computing instances used for running the experiments.
Software Dependencies No The paper mentions using Dyna and MPC solvers, neural network ensembles, and specific optimization methods like Adam (via citation), but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes Implementation details and hyperparameters are provided in Appendix F.1.