Additional videos in experiments

Comparative evaluations with two baselines

prop_env1_wo.mp4

SACSoN policy trained on our dataset

exaug_env1_wo.mp4

ExAug policy trained on our dataset

conv_env1_wo.mp4

SACSoN policy trained on naive dataset

prop_env2_wo.mp4

SACSoN policy trained on our dataset

exaug_env2_wo.mp4

ExAug policy trained on our dataset

conv_env2_wo.mp4

SACSoN policy trained on naive dataset

Evaluation with 17 human subjects (our method)

Dhruv.mp4

Ami.mp4

Isudora.mp4

Katie.mp4

Marwa.mp4

Niclas.mp4

Pranav.mp4

Zheyuan.mp4

Catherine.mp4

More videos for SACSoN policy

soc_video_1.mp4

soc_video_4.mp4

soc_video_2.mp4

soc_video_3.mp4

Acknowledgments

The authors would like to express their gratitude to Marwa Abdulhai, Qiyang Li, Manan Tomar, Mitsuhiko Nakamoto, Roxana Infante, Ami Katagiri, Katie Kang, Zheyuan Hu, Oier Mees, Jakub Grudzien Kuba, Pranav Atreya, Isadora White, Zhiyuan Zhou, Anjali Thakrar, Niclas Joswig, Kyle Stachowicz, and Catherine Glossop for their valuable assistance in evaluating the SACSoN.