clean

README.md

@@ -23,7 +23,7 @@ This repository is the implementation code of the CoRL 2023 Oral paper "MimicPla
 
 <img src="assets/method_fig.png" border=0 width=100%>
 
-In this repo, we provide our full implementation code of [training](#training) and [evaluation](#evaluation) in simulation and the [scripts to generate human play dataset](#human-play-data-processing) for experiments in the real-world. Note that, in our main paper, we leverage human play data. However, in simulation, there is no way to get such dataset, which will always end up be robot teleoperation. So in this repo, when training the high-level latent planner, we use the same robot play dataset to train both high-level planner and low-level policy, and reproduce the advantage of MimicPlay(0-human) over baselines in simulation. For real-world experiments, we provide the [process scripts for human play video](#human-play-data-processing), which generates the dataset that can directly used for training the high-level latent planner of this repo.
+In this repo, we provide our full implementation code of [training](#training) and [evaluation](#evaluation) in simulation and the [scripts to generate human play dataset](#human-play-data-processing) for experiments in the real-world. Note that, in our main paper, we leverage human play data. However, in simulation, there is no way to get such dataset, which will always end up be robot teleoperation. Therefore, in this repo, we use the same robot play dataset to train both high-level planner and low-level policy, and reproduce the advantage of MimicPlay(0-human) over baselines in simulation. For real-world experiments, we provide the [process scripts for human play video](#human-play-data-processing), which generates the dataset that can directly used for training the high-level latent planner of this repo.
 
 -------
 ## Installation