1 citations · 2 across the 5 of their papers we have counts for
6 papers
SACn: Soft Actor-Critic with n-step Returns
Jakub Łyskawa, Jakub Lewandowski, Paweł Wawrzyński
Soft Actor-Critic (SAC) is widely used in practical applications and is now one of the most relevant off-policy online model-free reinforcement learning (RL) methods. The technique…
Actor-Critic with variable time discretization via sustained actions
Jakub Łyskawa, Paweł Wawrzyński
Reinforcement learning (RL) methods work in discrete time. In order to apply RL to inherently continuous problems like robotic control, a specific time discretization needs to be d…
Detecting Out-of-distribution Objects Using Neuron Activation Patterns
Bartłomiej Olber, Krystian Radlak, Krystian Chachuła +2
Object detection is essential to many perception algorithms used in modern robotics applications. Unfortunately, the existing models share a tendency to assign high confidence scor…
Emergency action termination for immediate reaction in hierarchical reinforcement learning
Michał Bortkiewicz, Jakub Łyskawa, Paweł Wawrzyński +3
Hierarchical decomposition of control is unavoidable in large dynamical systems. In reinforcement learning (RL), it is usually solved with subgoals defined at higher policy levels…
Combating noisy labels in object detection datasets
Krystian Chachuła, Jakub Łyskawa, Bartłomiej Olber +3
The quality of training datasets for deep neural networks is a key factor contributing to the accuracy of resulting models. This effect is amplified in difficult tasks such as obje…
A framework for reinforcement learning with autocorrelated actions
Marcin Szulc, Jakub Łyskawa, Paweł Wawrzyński
The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instant…