Add talks to education.md

_config.yml

@@ -50,6 +50,9 @@ collections:
   news:
     output: false
     permalink: /:collection/:name
+  talks:
+    output: false
+    permalink: /:collection/:name
   research_areas:
     output: false
     permalink: /:collection/:name

_talks/2023-05-06-nuro-tech-talk.md

@@ -0,0 +1,7 @@
+---
+title: Contingency Games for Multi-Agent Interaction
+date: 2023-05-06
+speaker: Lasse Peters
+recording: https://www.youtube.com/watch?v=WVzK7yBejlU
+abstract: Contingency planning, wherein an agent generates a set of possible plans conditioned on the outcome of an uncertain event, is an increasingly popular way for robots to act under uncertainty. In this talk, it will be presented a game-theoretic perspective on contingency planning which is tailored to multi-agent scenarios in which a robot's actions impact the decisions of other agents and vice versa. The resulting contingency game allows the robot to efficiently coordinate with other agents by generating strategic motion plans conditioned on multiple possible intents of other actors in the scene. Beyond this new problem formulation, it will be (i) discussed an efficient method for solving $N$-player contingency games with nonlinear dynamics and non-convex costs and constraints, (ii) shown that this framework recovers existing variants of game-theoretic planning under uncertainty as special case, and (iii) demonstrated quantitative performance gains over game-theoretic motion plans that do not account for future uncertainty reduction.
+---

_talks/2024-02-21-cmu-guest-lecture.md

@@ -0,0 +1,7 @@
+---
+title: Game-Theoretic Models for Multi-Agent Interaction
+date: 2024-02-21
+speaker: Lasse Peters
+recording: https://www.youtube.com/watch?v=Jcw1C57G1eo
+abstract: When multiple agents operate in a common environment, their actions are naturally interdependent and this coupling complicates planning. In this lecture, we will approach this problem through the lens of dynamic game theory. We will discuss how to model multi-agent interactions as general-sum games over continuous states and actions, characterize solution concepts of such games, and highlight the key challenges of solving them in practice. Based on this foundation, we will review established techniques to tractably approximate game solutions for online decision-making. Finally, will discuss extensions of the game-theoretic framework to settings that involve incomplete knowledge about the intent, dynamics, or state of other agents.
+---

education.md

@@ -68,4 +68,20 @@ The motivation letter should state:
 
 # Recorded Talks
 
-Coming soon...
+<div class="row">
+    <div class="col">
+        <ul class="timeline">
+            {% assign talks = site.talks | sort: 'date' | reverse %}
+            {% for talk in talks %}
+            <li>
+                <span class="fw-bold"> {{ talk.date | date: "%B %d, %Y" }}, {{ talk.speaker }}: <a href="{{ talk.recording }}"> {{ talk.title }}</a></span>
+                <br>
+                <!-- render abstract if we have it -->
+                {% if talk.abstract %}
+                <span class="fw-bold">Abstract:</span> {{ talk.abstract }}
+                {% endif %}
+            </li>
+            {% endfor %}
+        </ul>
+    </div>
+</div>