diff --git a/_data/authors.yml b/_data/authors.yml
index 6c68d80..51190b3 100644
--- a/_data/authors.yml
+++ b/_data/authors.yml
@@ -1,4 +1,6 @@
 ---
+Ali:
+  firstname: ["Mohammad", "M.", "M. A.", "Mohammad Ali"]
 Alibeigi:
   firstname: ["Mina", "M.", "M. A.", "Mina Alibeigi"]
   github: alibeigi
@@ -13,14 +15,26 @@ Astrom:
   org: Lund University
   scholar: YIzs6eoAAAAJ
   title: Professor
+Basu:
+  firstname: ["Debabrota", "D.", "D. B.", "Debabrota Basu"]
+  scholar: e26Maa4AAAAJ
+Batkovic:
+  firstname: ["Ivo", "I.", "I. B.", "Ivo Batkovic"]
+  scholar: 7X_8eVEAAAAJ
 Bodin:
   firstname: ["Alexander", "A.", "A. B.", "Alexander Bodin"]
   org: Zenseact
   title: Intern
+Dimitrakakis:
+  firstname: ["Christos", "C.", "C. D.", "Christos Dimitrakakis"]
+  scholar: 9Kw4t_kAAAAJ
 EliasSvensson:
   firstname: ["Elias", "E.", "E. S.", "Elias Svensson"]
   org: Zenseact
   title: Intern
+Eriksson:
+  firstname: ["Hannes", "H.", "H. E.", "Hannes Eriksson"]
+  scholar: KyX9dfEAAAAJ
 Fatemi:
   firstname: ["Maryam", "M.", "M. F.", "Maryam Fatemi"]
   mail: maryam.fatemi@zenseact.com
@@ -42,10 +56,12 @@ Fu:
   scholar: z3lud1UAAAAJ
   title: Researcher
   url: https://junshengfu.github.io
+Gronberg:
+  firstname: ["Robin", "R.", "R. G.", "Robin Grönberg"]
 Hagerman:
   firstname: ["David", "D.", "D. H.", "David Hagerman"]
-  org: Zenseact
-  title: Intern
+  org: Chalmers University of Technology
+  scholar: VRDfJPAAAAAJ
 Hammarstrand:
   firstname: ["Lars", "L.", "L. H.", "Lars Hammarstrand"]
   org: Chalmers University of Technology
@@ -61,6 +77,11 @@ Hess:
   scholar: ZvUoV2EAAAAJ
   title: PhD Student
   url: https://georghess.github.io/
+Hoel:
+  firstname: ["Carl-Johan", "C.", "C. H.", "Carl-Johan Hoel"]
+  scholar: f7ewwIsAAAAJ
+Jansson:
+  firstname: ["Anton", "A.", "A. J.", "Anton Jansson"]
 Jaxing:
   firstname: ["Johan", "J.", "J. X.", "Johan Jaxing"]
   org: Zenseact
@@ -120,6 +141,9 @@ Rafidashti:
   mail: mahan.rafidashti@zenseact.com
   org: [Zenseact, Chalmers University of Technology]
   title: PhD Student
+Sjoberg:
+  firstname: ["Jonas", "J.", "J. S.", "Jonas Sjöberg"]
+  scholar: s0Qakg77XTYC
 Stenborg:
   firstname: ["Erik", "E.", "E. S.", "Erik Stenborg"]
   mail: erik.stenberg@zenseact.com
@@ -141,6 +165,11 @@ Tonderski:
   scholar: 2R5ZLp0AAAAJ
   title: PhD Student
   url: https://atonderski.github.io/
+Tram:
+  firstname: ["Tommy", "T.", "T. T.", "Tommy Tram"]
+  org: Zenseact
+  scholar: m_O_xjIAAAA
+  title: null
 Widahl:
   firstname: ["Jenny", "J.", "J.W.", "Jenny Widahl"]
   org: Zenseact
\ No newline at end of file
diff --git a/_data/venues.yml b/_data/venues.yml
index 81f4e8f..3f240b8 100644
--- a/_data/venues.yml
+++ b/_data/venues.yml
@@ -19,4 +19,13 @@ WACV23:
   url: https://wacv2023.thecvf.com
 WACV24:
   name: Winter Conference on Applications of Computer Vision (WACV), 2024
-  url: https://wacv2024.thecvf.com
\ No newline at end of file
+  url: https://wacv2024.thecvf.com
+ITSC20:
+  name: 2020 IEEE 23rd international conference on intelligent transportation systems (ITSC)
+  url: https://www.ieee-itsc2020.org/
+ITSC19:
+  name: 2019 IEEE Intelligent Transportation Systems Conference (ITSC)
+  url: https://ieee-itsc.org/2019/www.itsc2019.org/index.html
+ITSC18:
+  name: 2018 21st International Conference on Intelligent Transportation Systems (ITSC)
+  url: https://ieee-itsc.org/2018/
\ No newline at end of file
diff --git a/_publications/learning-when-to-drive/learning-when-to-drive.md b/_publications/learning-when-to-drive/learning-when-to-drive.md
new file mode 100644
index 0000000..2b5aeb0
--- /dev/null
+++ b/_publications/learning-when-to-drive/learning-when-to-drive.md
@@ -0,0 +1,17 @@
+---
+layout: publication
+permalink: /publications/learning-when-to-drive/
+title: "Learning When to Drive in Intersections by Combining Reinforcement Learning and Model Predictive Control"
+venue: ITSC19
+authors:
+  - Tram
+  - Batkovic
+  - Ali
+  - Sjoberg
+date: 2019-10-17 00:00:00 +00:00
+arxiv: https://ieeexplore.ieee.org/abstract/document/8916922
+n_equal_contrib: 1
+---
+
+# Abstract
+In this paper, we propose a decision making algorithm intended for automated vehicles that negotiate with other possibly non-automated vehicles in intersections. The decision algorithm is separated into two parts: a high-level decision module based on reinforcement learning, and a low-level planning module based on model predictive control. Traffic is simulated with numerous predefined driver behaviors and intentions, and the performance of the proposed decision algorithm was evaluated against another controller. The results show that the proposed decision algorithm yields shorter training episodes and an increased performance in success rate compared to the other controller.
\ No newline at end of file
diff --git a/_publications/mtrl/mtrl.md b/_publications/mtrl/mtrl.md
new file mode 100644
index 0000000..fbf9289
--- /dev/null
+++ b/_publications/mtrl/mtrl.md
@@ -0,0 +1,18 @@
+---
+layout: publication
+permalink: /publications/mtrl/
+title: "Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer"
+venue: ARXIV
+authors:
+  - Eriksson
+  - Basu
+  - Tram
+  - Alibeigi
+  - Dimtrakakis
+date: 2023-02-18 00:00:00 +00:00
+arxiv: https://arxiv.org/pdf/2302.09273.pdf
+n_equal_contrib: 1
+---
+
+# Abstract
+In this paper, we study the problem of transferring the available Markov Decision Process (MDP) models to learn and plan efficiently in an unknown but similar MDP. We refer to it as \textit{Model Transfer Reinforcement Learning (MTRL)} problem. First, we formulate MTRL for discrete MDPs and Linear Quadratic Regulators (LQRs) with continuous state actions. Then, we propose a generic two-stage algorithm, MLEMTRL, to address the MTRL problem in discrete and continuous settings. In the first stage, MLEMTRL uses a \textit{constrained Maximum Likelihood Estimation (MLE)}-based approach to estimate the target MDP model using a set of known MDP models. In the second stage, using the estimated target MDP model, MLEMTRL deploys a model-based planning algorithm appropriate for the MDP class. Theoretically, we prove worst-case regret bounds for MLEMTRL both in realisable and non-realisable settings. We empirically demonstrate that MLEMTRL allows faster learning in new MDPs than learning from scratch and achieves near-optimal performance depending on the similarity of the available MDPs and the target MDP.
\ No newline at end of file
diff --git a/_publications/negotiating-behavior-using-q-learning/negotiating-behavior-using-q-learning.md b/_publications/negotiating-behavior-using-q-learning/negotiating-behavior-using-q-learning.md
new file mode 100644
index 0000000..d535605
--- /dev/null
+++ b/_publications/negotiating-behavior-using-q-learning/negotiating-behavior-using-q-learning.md
@@ -0,0 +1,18 @@
+---
+layout: publication
+permalink: /publications/negotiating-behavior-using-q-learning/
+title: "Learning Negotiating Behavior Between Cars in Intersections using Deep Q-Learning"
+venue: ITSC18
+authors:
+  - Tram
+  - Jansson
+  - Gronberg
+  - Ali
+  - Sjoberg
+date: 2018-11-04 00:00:00 +00:00
+arxiv: https://ieeexplore.ieee.org/abstract/document/8569316
+n_equal_contrib: 1
+---
+
+# Abstract
+This paper concerns automated vehicles negotiating with other vehicles, typically human driven, in crossings with the goal to find a decision algorithm by learning typical behaviors of other vehicles. The vehicle observes distance and speed of vehicles on the intersecting road and use a policy that adapts its speed along its pre-defined trajectory to pass the crossing efficiently. Deep Q-learning is used on simulated traffic with different predefined driver behaviors and intentions. The results show a policy that is able to cross the intersection avoiding collision with other vehicles 98% of the time, while at the same time not being too passive. Moreover, inferring information over time is important to distinguish between different intentions and is shown by comparing the collision rate between a Deep Recurrent Q-Network at 0.85% and a Deep Q-learning at 1.75%.
\ No newline at end of file
diff --git a/_publications/tactical-decisions-in-intersections/tactical-decisions-in-intersections.md b/_publications/tactical-decisions-in-intersections/tactical-decisions-in-intersections.md
new file mode 100644
index 0000000..8549d11
--- /dev/null
+++ b/_publications/tactical-decisions-in-intersections/tactical-decisions-in-intersections.md
@@ -0,0 +1,16 @@
+---
+layout: publication
+permalink: /publications/tactical-decisions-in-intersections/
+title: "Reinforcement Learning with Uncertainty Estimation for Tactical Decision-Making in Intersections"
+venue: ITSC20
+authors:
+  - Hoel
+  - Tram
+  - Sjoberg
+date: 2020-09-20 00:00:00 +00:00
+arxiv: https://ieeexplore.ieee.org/abstract/document/9294407
+n_equal_contrib: 1
+---
+
+# Abstract
+This paper investigates how a Bayesian reinforcement learning method can be used to create a tactical decision-making agent for autonomous driving in an intersection scenario, where the agent can estimate the confidence of its decisions. An ensemble of neural networks, with additional randomized prior functions (RPF), are trained by using a bootstrapped experience replay memory. The coefficient of variation in the estimated Q-values of the ensemble members is used to approximate the uncertainty, and a criterion that determines if the agent is sufficiently confident to make a particular decision is introduced. The performance of the ensemble RPF method is evaluated in an intersection scenario and compared to a standard Deep Q-Network method, which does not estimate the uncertainty. It is shown that the trained ensemble RPF agent can detect cases with high uncertainty, both in situations that are far from the training distribution, and in situations that seldom occur within the training distribution. This work demonstrates one possible application of such a confidence estimate, by using this information to choose safe actions in unknown situations, which removes all collisions from within the training distribution, and most collisions outside of the distribution.
\ No newline at end of file