add machiavelli

Author: aypan17

_pages/about.md

@@ -8,24 +8,27 @@ redirect_from:
   - /about.html
 ---
 
-Hello! I am a first-year CS PhD student at Berkeley, where I am fortunate to be advised by [Jacob Steinhardt](https://jsteinhardt.stat.berkeley.edu/) and grateful to be supported by a [FLI PhD fellowship](https://futureoflife.org/about-us/our-people/fellowship-winners-2022/). I am interested in aligning adaptive ML systems.
+Hello! I am a first-year CS PhD student at Berkeley, where I am fortunate to be advised by [Jacob Steinhardt](https://jsteinhardt.stat.berkeley.edu/). I am interested in aligning adaptive ML systems, especially sequential decision-making agents. I am grateful to be supported by a [FLI PhD fellowship](https://futureoflife.org/about-us/our-people/fellowship-winners-2022/).
 
 I studied mathematics and computer science at Caltech, where I worked with [Anima Anandkumar](http://tensorlab.cms.caltech.edu/users/anima/) and [Yuanyuan Shi](https://yyshi.eng.ucsd.edu/).  
 
 See [here](https://drive.google.com/file/d/17jkbEmK-c69u8qqnYDzJNbo917Qwn6gg/view?usp=sharing) for my CV. 
 
-Outside of work I enjoy baking, [reading](https://www.goodreads.com/user/show/71787702-alex-pan), and fashion.
-
 Publications
 ======
+[Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark](https://arxiv.org/abs/2304.03279)
+Alexander Pan\*, Chan Jun Shern\*, Andy Zou\*, Nathaniel Li, Steven Basart, Thomas Woodside, Jonathan Ng, Hanlin Zhang, Scott Emmons, Dan Hendrycks
+Preprint 2023
+[pdf](https://arxiv.org/pdf/2304.03279.pdf) / [code](https://github.com/aypan17/machiavelli) / [website](https://aypan17.github.io/machiavelli/)
+
 [The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models](https://arxiv.org/abs/2201.03544)  
-**Alexander Pan**, Kush Bhatia, Jacob Steinhardt  
-*ICLR 2022.*    
+Alexander Pan, Kush Bhatia, Jacob Steinhardt  
+ICLR 2022
 [pdf](https://arxiv.org/abs/2201.03544) / [code](https://github.com/aypan17/reward-misspecification)
 
 [Improving Robustness of RL for Power System Control with Adversarial Training](https://arxiv.org/abs/2110.08956)  
-**Alexander Pan**, Yongkyun (Daniel) Lee, Huan Zhang, Yize Chen, Yuanyuan Shi    
-*ICML RL4RL Workshop 2021.*    
+Alexander Pan, Yongkyun (Daniel) Lee, Huan Zhang, Yize Chen, Yuanyuan Shi    
+ICML RL4RL Workshop 2021   
 [pdf](https://arxiv.org/abs/2110.08956) / [code](https://github.com/aypan17/robust_pn)
 
 <!---

assets/css/academicons.css

@@ -324,4 +324,7 @@
 }
 .fa.fa-pull-right {
   margin-left: .3em;
-}
+}
+footer a:link {
+  text-decoration: none !important;
+ }

assets/css/main.scss

@@ -10,6 +10,10 @@
  *
 */
 
+footer a:link {
+    text-decoration: none !important;
+   }
+
 @import "vendor/breakpoint/breakpoint"; // media query mixins
 @import "variables";
 @import "mixins";