64 citations · 139 across the 9 of their papers we have counts for
9 papers
On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks
Maximilian Seitzer, Arash Tavakoli, Dimitrije Antic +1
Capturing aleatoric uncertainty is a critical part of many machine learning systems. In deep learning, a common approach to this end is to train a neural network to estimate the pa…
Orchestrated Value Mapping for Reinforcement Learning
Mehdi Fatemi, Arash Tavakoli
We present a general convergent class of reinforcement learning algorithms that is founded on two distinct principles: (1) mapping value estimates to a different space using arbitr…
Learning to Represent Action Values as a Hypergraph on the Action Vertices
Arash Tavakoli, Mehdi Fatemi, Petar Kormushev
Action-value estimation is a critical component of many reinforcement learning (RL) methods whereby sample complexity relies heavily on how fast a good estimator for action value c…
A neural network oracle for quantum nonlocality problems in networks
Tamás Kriváchy, Yu Cai, Daniel Cavalcanti +3
Characterizing quantum nonlocality in networks is a challenging, but important problem. Using quantum sources one can achieve distributions which are unattainable classically. A ke…
Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning
Harm van Seijen, Mehdi Fatemi, Arash Tavakoli
In an effort to better understand the different ways in which the discount factor affects the optimization process in reinforcement learning, we designed a set of experiments to st…
Exploring Restart Distributions
Arash Tavakoli, Vitaly Levdik, Riashat Islam +2
We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution. That is, given the capacity to reset the state with those cor…
Time Limits in Reinforcement Learning
Fabio Pardo, Arash Tavakoli, Vitaly Levdik +1
In reinforcement learning, it is common to let an agent interact for a fixed amount of time with its environment before resetting it and repeating the process in a series of episod…
Action Branching Architectures for Deep Reinforcement Learning
Arash Tavakoli, Fabio Pardo, Petar Kormushev
Discrete-action algorithms have been central to numerous recent successes of deep reinforcement learning. However, applying these algorithms to high-dimensional action tasks requir…
Multiplayer Games for Learning Multirobot Coordination Algorithms
Arash Tavakoli, Haig Nalbandian, Nora Ayanian
Humans have an impressive ability to solve complex coordination problems in a fully distributed manner. This ability, if learned as a set of distributed multirobot coordination str…