Hi, I am Marin, a PhD student at the Max Planck Institute for Intelligent Systems in Tuebingen, Germany as part of the International Max Planck Research School for Intelligent Systems. My thesis advisory committee consists of Georg Martius, Peter Dayan, Michael Muehlebach and Aamir Ahmad, with my primary supervisor being Georg Martius.
I possess a masters degree in computer science with a machine learning focus from the Karlsruhe Institute of Technology, Karlsruhe, Germany and a bachelors degree in computer science from the University of Zagreb, Croatia.
In 2017 I was fortunate enough to have received a research fellowship with the Blue Brain Project in Geneva, Switzerland, where I came into contact with neuroscience. In 2021 I spent some time at Amazon as an applied scientist intern doing work on variational inference, reinforcement learning and NLP in collaboration with Patrick Ernst and Gyuri Szarvas. I spent part of 2022 at DeepMind hosted by Kimberly Stachenfeld in Peter Battaglia's group working on diffusion generative modelling for building better optimizers in close collaboration with Arnaud Doucet.
Regarding research, I have a broad interest in sequential decision making (RL etc.), representation learning, generative modelling and implicit layers. I am actively looking for collaborators! If you are interested, you can reach me at mvlastelica at tue dot mpg dot de.
In my free time I enjoy playing guitar, reading opinionated books on various topics, and all sorts of sport activities.
We show that Fenchel duality can be utilized to maximize a diversity objective subject to f-divergence constraints.
We propose an improved sampling procedure for a diffusion generative model for approximate sampling from a target distribution that is defined by an energy (cost) function of designs in a complex simulation environment.
In this work we proposed a method for imitating rough demonstrations by a robot quadruped based on Wasserstein adversarial learning of an imitation reward. We trained a policy via domain randomization and successfully transferred it to the real system, where to robot was able to reproduce agile motions.
As a continuation of the blackbox-backprop line of work, we introduce a simple modification to the algorith, namely treating the solver as an identity mapping in the computation graph on the backward pass.
This, coupled with projections that avoid degenerate cases, works comparably well as
Adversarial learning to facilitate unsupervised skill discovery resulting in a controllable skill set by a latent variable with skills that are useful for solving the downstream task.
In this work we address the problem of efficient uncertainty estimation in zero-order trajectory optimization via the Cross Entropy Method (CEM). Moreover, we show that it is essential that we can distinguish between epistemic and aleatoric uncertainty in order to avoid so-called “risky” behaviour.
Latent action reinforcement learning for task-oriented dialogue has seen success at benchmarks such as MultiWOZ. Categorical latents have been argued to be the best choice. We show that with continuous latents and reformulation of the ELBO objective and the reinforcmenet learning stage, we can achieve state-of-the-art performance on MultiWOZ.
As a continuation of the blackbox-differentiation line of work, we propose to use time-dependent shortest-path solvers in order to enhance generalization capabilities of neural network policies. With imposing a prior on the underlying goal-conditioned MDP structure, we are able to extract well-performing policies through imitation learning that utilize blackbox solvers for receding horizon planning at execution time. Again, this comes with absolutely no sacrifices to the optimality of the solver used.
As another continuation of the blackbox differentiation line of work, we show that we can cast the ranking problem as a blackbox solver that satisfies the conditions for efficient gradient calculation, therefore enabling us to optimize rank-based metrics by simply using efficient implementations of sorting algorithms instead of learning a differentiable sort operation. We apply this insight to optimizing mean average precision and recall in object detection and retrieval tasks, where we achieve comparable results to state-of-the-art at the time.
Problems that are inherently combinatorial still remain a hinderance for classical deep learning methods. Traditional methods that try to do gradient propagation through combinatorial solvers rely on sample-based estimates or solver relaxations. We show that for a specific class of solver, we are able to efficiently compute gradients of an implicit piecewise-linear interpolation of the objective. This allows us to achieve unprecedented generalization performance on representation learning tasks with combinatorial flavor.
In this work we propose a hierarchical reinforcement learning algorithm that is able to construct planning graphs while managing to use computational resources efficiently, guided by intrinsic motivation in form of prediction error and measure of task improvement.
In this work we propose a liquid state machine approach to reinforcement learning of continuous motor control. The liquid state machine approach with smart spectral radius initialization has shown to extract useful features for motor control which can be used with classical RL algorithms.
In this work we looked at what kind of features we can use for prediction of video valence, violence and sentiment.
Developing a Python package with standard normalizing flow implementations that is based on
As part of hackathon, we have noticed that the future of energy distribution networks are with small producers (via solar cells for example). The missing component is an exchange that makes it possible for producers to exchange energy for value, which we tried to make possible. With this, we have won 1st place on a Microsoft-organized hackathon Germany-wide.