29 citations · 144 across the 19 of their papers we have counts for
22 papers
Continuous Control With Ensemble Deep Deterministic Policy Gradients
Piotr Januszewski, Mateusz Olko, Michał Królikowski +4
The growth of deep reinforcement learning (RL) has brought multiple exciting tools and methods to the field. This rapid expansion makes it important to understand the interplay bet…
Off-Policy Correction For Multi-Agent Reinforcement Learning
Michał Zawalski, Błażej Osiński, Henryk Michalewski +1
Multi-agent reinforcement learning (MARL) provides a framework for problems involving multiple interacting agents. Despite apparent similarity to the single-agent case, multi-agent…
Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
Łukasz Kuciński, Tomasz Korbak, Paweł Kołodziej +1
Communication is compositional if complex signals can be represented as a combination of simpler subparts. In this paper, we theoretically show that inductive biases on both the tr…
Subgoal Search For Complex Reasoning Tasks
Konrad Czechowski, Tomasz Odrzygóźdź, Marek Zbysiński +5
Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propose Subgoal Search (kSubS) method. Its k…
Continual World: A Robotic Benchmark For Continual Reinforcement Learning
Maciej Wołczyk, Michał Zając, Razvan Pascanu +2
Continual learning (CL) -- the ability to continuously learn, building on previously acquired knowledge -- is a natural requirement for long-lived autonomous reinforcement learning…
Planning and Learning Using Adaptive Entropy Tree Search
Piotr Kozakowski, Mikołaj Pacek, Piotr Miłoś
Recent breakthroughs in Artificial Intelligence have shown that the combination of tree-based planning with deep learning can lead to superior performance. We present Adaptive Entr…