Robust Imitation of Diverse Behaviors

Authors: Ziyu Wang, Josh S. Merel, Scott E. Reed, Nando de Freitas, Gregory Wayne, Nicolas Heess

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate our approach on learning diverse gaits from demonstration on a 2D biped and a 62 Do F 3D humanoid in the Mu Jo Co physics environment.
Researcher Affiliation Industry Deep Mind ziyu,jsmerel,reedscot,gregwayne,nandodefreitas,heess@google.com
Pseudocode Yes Algorithm 1 Diverse generative adversarial imitation learning.
Open Source Code No The paper does not provide an explicit statement or link for the open-source code for the methodology described.
Open Datasets Yes The training set consists of 250 random trajectories from 6 different neural network controllers that were trained to match 6 different movement styles from the CMU motion capture data base4.
Dataset Splits No The paper describes training and test data generation/usage, but does not explicitly mention a distinct validation set or specific splits for it.
Hardware Specification No The paper mentions the use of the Mu Jo Co physics engine for simulations but does not specify any hardware details such as GPU or CPU models used for running experiments.
Software Dependencies No The paper mentions software components like MuJoCo, LSTM, WaveNet, and TRPO, but does not specify their version numbers or other detailed software dependencies required for replication.
Experiment Setup Yes For details of the simulation and the experimental setup please see appendix.