Piotr Miłoś | DeepAI

DeepAI AI Chat

Featured Co-authors

Sergey Levine
366 publications
Chelsea Finn
155 publications
Zhibo Chen
105 publications
Razvan Pascanu
79 publications
Tomasz Trzciński
70 publications
Stefan Bauer
64 publications
Chun Yuan
52 publications
Jakub M. Tomczak
43 publications
Stephen J. Roberts
42 publications
George Tucker
39 publications
Shuchang Zhou
37 publications

∙ 05/31/2023

The Tunnel Effect: Building Data Representations in Deep Neural Networks

Deep neural networks are widely known for their remarkable effectiveness...

0 Wojciech Masarczyk, et al. ∙

∙ 03/27/2023

Exploring Continual Learning of Diffusion Models

Diffusion models have achieved remarkable success in generating high-qua...

0 Michał Zając, et al. ∙

∙ 03/08/2023

Magnushammer: A Transformer-based Approach to Premise Selection

Premise selection is a fundamental problem of automated theorem proving....

0 Maciej Mikuła, et al. ∙

∙ 11/29/2022

The Surprising Effectiveness of Latent World Models for Continual Reinforcement Learning

We study the use of model-based reinforcement learning methods, in parti...

0 Samuel Kessler, et al. ∙

∙ 11/24/2022

Trust Your ∇: Gradient-based Intervention Targeting for Causal Discovery

Inferring causal structure from data is a challenging task of fundamenta...

0 Mateusz Olko, et al. ∙

∙ 09/28/2022

Disentangling Transfer in Continual Reinforcement Learning

The ability of continual learning systems to transfer knowledge from pre...

0 Maciej Wołczyk, et al. ∙

∙ 06/01/2022

Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search

Complex reasoning problems contain states that vary in the computational...

0 Michał Zawalski, et al. ∙

∙ 05/22/2022

Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers

In theorem proving, the task of selecting useful premises from a large l...

0 Albert Q. Jiang, et al. ∙

∙ 11/30/2021

Continuous Control With Ensemble Deep Deterministic Policy Gradients

The growth of deep reinforcement learning (RL) has brought multiple exci...

0 Piotr Januszewski, et al. ∙

∙ 11/22/2021

Off-Policy Correction For Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) provides a framework for probl...

0 Michał Zawalski, et al. ∙

∙ 11/11/2021

Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication

Communication is compositional if complex signals can be represented as ...

0 Łukasz Kuciński, et al. ∙

∙ 08/25/2021

Subgoal Search For Complex Reasoning Tasks

Humans excel in solving complex reasoning tasks through a mental process...

5 Konrad Czechowski, et al. ∙

∙ 05/23/2021

Continual World: A Robotic Benchmark For Continual Reinforcement Learning

Continual learning (CL) – the ability to continuously learn, building on...

0 Maciej Wołczyk, et al. ∙

∙ 02/12/2021

Robust and Efficient Planning using Adaptive Entropy Tree Search

In this paper, we present the Adaptive EntropyTree Search (ANTS) algorit...

0 Piotr Kozakowski, et al. ∙

∙ 12/16/2020

CARLA Real Traffic Scenarios – novel training ground and benchmark for autonomous driving

This work introduces interactive traffic scenarios in the CARLA simulato...

0 Błażej Osiński, et al. ∙

∙ 12/19/2019

Uncertainty-sensitive Learning and Planning with Ensembles

We propose a reinforcement learning framework for discrete environments ...

21 Piotr Miłoś, et al. ∙

∙ 11/29/2019

Simulation-based reinforcement learning for real-world autonomous driving

We use synthetic data and a reinforcement learning algorithm to train a ...

0 Błażej Osiński, et al. ∙

∙ 10/04/2019

Developmentally motivated emergence of compositional communication via template transfer

This paper explores a novel approach to achieving emergent compositional...

0 Tomasz Korbak, et al. ∙

∙ 03/01/2019

Model-Based Reinforcement Learning for Atari

Model-free reinforcement learning (RL) can be used to learn effective po...

20 Łukasz Kaiser, et al. ∙

∙ 09/10/2018

Expert-augmented actor-critic for ViZDoom and Montezumas Revenge

We propose an expert-augmented actor-critic algorithm, which we evaluate...

2 Michał Garmulewicz, et al. ∙

∙ 04/02/2018

Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments

In the NIPS 2017 Learning to Run challenge, participants were tasked wit...

0 Łukasz Kidziński, et al. ∙