291 citations · 295 across the 7 of their papers we have counts for
9 papers
What Emerges and What Breaks in Self-Play Driving
Laur Sisask, Ardi Tampuu, Tambet Matiisen
Training autonomous driving policies through pure self-play has recently shown promising results. Following Gigaflow and Puffer- Drive, we train driving policies in a similar self-…
How Uncertainty Estimation Scales with Sampling in Reasoning Models
Maksym Del, Markus Kängsepp, Marharyta Domnich +4
Uncertainty estimation is critical for deploying reasoning language models, yet remains poorly understood under extended chain-of-thought reasoning. We study parallel sampling as a…
Combating the effects of speed and delays in end-to-end self-driving
Ardi Tampuu, Ilmar Uduste, Kristjan Roosild
In the behavioral cloning approach to end-to-end driving, a dataset of expert driving is collected and the model learns to guess what the expert would do in different situations. S…
Controlling Steering with Energy-Based Models
Mikita Balesni, Ardi Tampuu, Tambet Matiisen
So-called implicit behavioral cloning with energy-based models has shown promising results in robotic manipulation tasks. We tested if the method's advantages carry on to controlli…
LiDAR-as-Camera for End-to-End Driving
Ardi Tampuu, Romet Aidla, Jan Are van Gent +1
The core task of any autonomous driving system is to transform sensory inputs into driving commands. In end-to-end driving, this is achieved via a neural network, with one or multi…
A Survey of End-to-End Driving: Architectures and Training Methods
Ardi Tampuu, Maksym Semikin, Naveed Muhammad +2
Autonomous driving is of great interest to industry and academia alike. The use of machine learning approaches for autonomous driving has long been studied, but mostly in the conte…
Perspective Taking in Deep Reinforcement Learning Agents
Aqeel Labash, Jaan Aru, Tambet Matiisen +2
Perspective taking is the ability to take the point of view of another agent. This skill is not unique to humans as it is also displayed by other animals like chimpanzees. It is an…
APES: a Python toolbox for simulating reinforcement learning environments
Aqeel Labash, Ardi Tampuu, Tambet Matiisen +2
Assisted by neural networks, reinforcement learning agents have been able to solve increasingly complex tasks over the last years. The simulation environment in which the agents in…
Multiagent Cooperation and Competition with Deep Reinforcement Learning
Ardi Tampuu, Tambet Matiisen, Dorian Kodelja +5
Multiagent systems appear in most social, economical, and political situations. In the present work we extend the Deep Q-Learning Network architecture proposed by Google DeepMind t…