393 citations · 835 across the 28 of their papers we have counts for
13 papers · 1 filter
Is Temporal Difference Learning the Gold Standard for Stitching in RL?
Michał Bortkiewicz, Władysław Pałucki, Mateusz Ostaszewski +1
Reinforcement learning (RL) promises to solve long-horizon tasks even when training data contains only short fragments of the behaviors. This experience stitching capability is oft…
Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning
Rafał Surdej, Michał Bortkiewicz, Alex Lewandowski +2
Trainable activation functions, whose parameters are optimized alongside network weights, offer increased expressivity compared to fixed activation functions. Specifically, trainab…
PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors
Yimeng Chen, Piotr Piȩkos, Mateusz Ostaszewski +2
Evaluating the scientific discovery capabilities of large language model based agents, particularly how they cope with varying environmental complexity and utilize prior knowledge,…
Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization
Wojciech Masarczyk, Mateusz Ostaszewski, Tin Sum Cheng +3
The softmax function is a fundamental building block of deep neural networks, commonly used to define output distributions in classification tasks or attention weights in transform…
Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control
Michal Nauman, Mateusz Ostaszewski, Krzysztof Jankowski +2
Sample efficiency in Reinforcement Learning (RL) has traditionally been driven by algorithmic enhancements. In this work, we demonstrate that scaling can also lead to substantial i…
A Case for Validation Buffer in Pessimistic Actor-Critic
Michal Nauman, Mateusz Ostaszewski, Marek Cygan
In this paper, we investigate the issue of error accumulation in critic networks updated via pessimistic temporal difference objectives. We show that the critic approximation error…
Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
Michal Nauman, Michał Bortkiewicz, Piotr Miłoś +3
Recent advancements in off-policy Reinforcement Learning (RL) have significantly improved sample efficiency, primarily due to the incorporation of various forms of regularization t…
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
Maciej Wołczyk, Bartłomiej Cupiał, Mateusz Ostaszewski +5
Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained capabilities, as recently showcased by the successful applications of foundation models. How…
On consequences of finetuning on data with highly discriminative features
Wojciech Masarczyk, Tomasz Trzciński, Mateusz Ostaszewski
In the era of transfer learning, training neural networks from scratch is becoming obsolete. Transfer learning leverages prior knowledge for new tasks, conserving computational res…
The Tunnel Effect: Building Data Representations in Deep Neural Networks
Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani +3
Deep neural networks are widely known for their remarkable effectiveness across various tasks, with the consensus that deeper networks implicitly learn more complex data representa…
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…
The Effectiveness of World Models for Continual Reinforcement Learning
Samuel Kessler, Mateusz Ostaszewski, Michał Bortkiewicz +5
World models power some of the most efficient reinforcement learning algorithms. In this work, we showcase that they can be harnessed for continual learning - a situation when the…
Reinforcement learning with experience replay and adaptation of action dispersion
Paweł Wawrzyński, Wojciech Masarczyk, Mateusz Ostaszewski
Effective reinforcement learning requires a proper balance of exploration and exploitation defined by the dispersion of action distribution. However, this balance depends on the ta…