Update README

README.md

@@ -12,13 +12,16 @@ This repository contains the official implementation for the paper "Versatile Lo
 
 [**Project Website**](https://relic-locoman.rai-inst.com/) | [**arXiv Paper**](https://arxiv.org/abs/2506.07876) | [**Blog Post**](https://rai-inst.com/resources/blog/reinforcement-learning-for-flexible-loco-manipulation/) | [**X**](https://x.com/rai_inst/status/1971590845817045218) | [**Threads**](https://www.threads.com/@robotics_and_ai_institute/post/DPEdj0UFEnm?xmt=AQF0fkVTtJFB-UTiEjOQATobby44KSl_DdfDymPMpr42Vg)
 
----
 *Our ReLIC policy enables a quadruped robot to walk with three legs and manipulate with the arm and one leg.*
 
 ## Overview
 
 **Reinforcement Learning for Interlimb Coordination (ReLIC)** is an approach that enables versatile loco-manipulation through flexible interlimb coordination. The core of our method is a single, adaptive controller that learns to seamlessly coordinate all of a robot's limbs. It intelligently bridges the execution of precise manipulation motions with the generation of stable, dynamic gaits, allowing the robot to interact with its environment in a versatile and robust manner.
 
+<p align="center">
+  <img src="figs/teaser.jpg" alt="ReLIC Manipulation" width="1024"/>
+</p>
+
 ## Install
 This project uses [Pixi](https://pixi.sh/latest/installation/) to manage dependencies and ensure a consistent development environment. You won't need to use `conda` or `virtualenv` separately or manually install `IsaacSim` or `IsaacLab`. Just follow the steps below to get started.
 
@@ -44,7 +47,7 @@ This project uses [Pixi](https://pixi.sh/latest/installation/) to manage depende
 
 Alternatively, you can install the project without Pixi by following the standard installation guides for [IsaacLab](https://isaac-sim.github.io/IsaacLab/v2.1.0/source/setup/installation/isaaclab_pip_installation.html) and its [extensions](https://github.com/isaac-sim/IsaacLabExtensionTemplate/tree/main?tab=readme-ov-file#installation).
 
-## Training and Eval
+## Train and Play
 
 ```bash
 python scripts/rsl_rl/train.py --task Isaac-Spot-Interlimb-Phase-1-v0 --headless
@@ -53,13 +56,23 @@ python scripts/rsl_rl/play.py --task Isaac-Spot-Interlimb-Play-v0 --center
 
 To achieve optimal deployment results, we implemented a weight curriculum with multiple training phases. Users can fine-tune the models from `Phase-2` to `Phase-4` to reproduce the results presented in our paper. The pre-trained weights can be found in `relic/source/relic/relic/assets/spot/pretrained`.
 
-## Deployment
-
-Please find deployment code with Boston Dynamics's Spot robot at our deployment branch.
-
-## Adapted Code
+## Citation
+```
+@inproceedings{
+    zhu2025versatile,
+    title={Versatile Loco-Manipulation through Flexible Interlimb Coordination},
+    author={Xinghao Zhu and Yuxin Chen and Lingfeng Sun and Farzad Niroui and Simon Le Cleac'h and Jiuguang Wang and Kuan Fang},
+    booktitle={9th Annual Conference on Robot Learning},
+    year={2025},
+    url={https://openreview.net/forum?id=Spg25qkV81}
+}
+```
 
-We use RSL_RL for RL training and adapt the following scripts from [IsaacLabExtensionTemplate](https://github.com/isaac-sim/IsaacLabExtensionTemplate/tree/main?tab=readme-ov-file#installation)
-- `scripts/rsl_rl/*`
+## Third-Party Code
+We use RSL_RL for RL training and adapt the following scripts from [IsaacLabExtensionTemplate](https://github.com/isaac-sim/IsaacLabExtensionTemplate/tree/main?tab=readme-ov-file#installation).
+- `scripts/rsl_rl`
 - `source/relic/pyproject.toml`
 - `source/relic/setup.py`
+
+## Disclaimer
+This code is provided as a research prototype and is not production-quality software. Please note that the code may contain missing features and potential bugs. As part of this release, the RAI Institute does not offer maintenance or support for the software.