Piotr Kozakowski

Mikołaj Sacha, Michał Sadowski, Piotr Kozakowski et al.

Retrosynthesis involves determining a sequence of reactions to synthesize complex molecules from simpler precursors. As this poses a challenge in organic chemistry, machine learning has offered solutions, particularly for predicting possible reaction substrates for a given target molecule. These solutions mainly fall into template-based and template-free categories. The former is efficient but relies on a vast set of predefined reaction patterns, while the latter, though more flexible, can be computationally intensive and less interpretable. To address these issues, we introduce METRO (Molecule-Edit Templates for RetrOsynthesis), a machine-learning model that predicts reactions using minimal templates - simplified reaction patterns capturing only essential molecular changes - reducing computational overhead and achieving state-of-the-art results on standard benchmarks.

Łukasz Kuciński, Witold Drzewakowski, Mateusz Olko et al.

Time series methods are of fundamental importance in virtually any field of science that deals with temporally structured data. Recently, there has been a surge of deterministic transformer models with time series-specific architectural biases. In this paper, we go in a different direction by introducing tsGT, a stochastic time series model built on a general-purpose transformer architecture. We focus on using a well-known and theoretically justified rolling window backtesting and evaluation protocol. We show that tsGT outperforms the state-of-the-art models on MAD and RMSE, and surpasses its stochastic peers on QL and CRPS, on four commonly used datasets. We complement these results with a detailed analysis of tsGT's ability to model the data distribution and predict marginal quantile values.

Michal Sadowski, Tadija Radusinović, Maria Wyrzykowska et al.

Retrosynthesis is one of the domains transformed by the rise of generative models, and it is one where the problem of nonsensical or erroneous outputs (hallucinations) is particularly insidious: reliable assessment of synthetic plans is time-consuming, with automatic methods lacking. In this work, we present RetroTrim, a retrosynthesis system that successfully avoids nonsensical plans on a set of challenging drug-like targets. Compared to common baselines in the field, our system is not only the sole method that succeeds in filtering out hallucinated reactions, but it also results in the highest number of high-quality paths overall. The key insight behind RetroTrim is the combination of diverse reaction scoring strategies, based on machine learning models and existing chemical databases. We show that our scoring strategies capture different classes of hallucinations by analyzing them on a dataset of labeled retrosynthetic intermediates. This approach formed the basis of our winning solution to the Standard Industries \$1 million Retrosynthesis Challenge. To measure the performance of retrosynthesis systems, we propose a novel evaluation protocol for reactions and synthetic paths based on a structured review by expert chemists. Using this protocol, we compare systems on a set of 32 novel targets, curated to reflect recent trends in drug structures. While the insights behind our methodology are broadly applicable to retrosynthesis, our focus is on targets in the drug-like domain. By releasing our benchmark targets and the details of our evaluation protocol, we hope to inspire further research into reliable retrosynthesis.

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 Entropy Tree Search (ANTS) - a novel algorithm combining planning and learning in the maximum entropy paradigm. Through a comprehensive suite of experiments on the Atari benchmark we show that ANTS significantly outperforms PUCT, the planning component of the state-of-the-art AlphaZero system. ANTS builds upon recent work on maximum entropy planning methods - which however, as we show, fail in combination with learning. ANTS resolves this issue to reach state-of-the-art performance. We further find that ANTS exhibits superior robustness to different hyperparameter choices, compared to the previous algorithms. We believe that the high performance and robustness of ANTS can bring tree search planning one step closer to wide practical adoption.

Piotr Kozakowski, Łukasz Kaiser, Henryk Michalewski et al.

Sample efficiency and performance in the offline setting have emerged as significant challenges of deep reinforcement learning. We introduce Q-Value Weighted Regression (QWR), a simple RL algorithm that excels in these aspects. QWR is an extension of Advantage Weighted Regression (AWR), an off-policy actor-critic algorithm that performs very well on continuous control tasks, also in the offline setting, but has low sample efficiency and struggles with high-dimensional observation spaces. We perform an analysis of AWR that explains its shortcomings and use these insights to motivate QWR. We show experimentally that QWR matches the state-of-the-art algorithms both on tasks with continuous and discrete actions. In particular, QWR yields results on par with SAC on the MuJoCo suite and - with the same set of hyperparameters - yields results on par with a highly tuned Rainbow implementation on a set of Atari games. We also verify that QWR performs well in the offline RL setting.

Piotr Miłoś, Łukasz Kuciński, Konrad Czechowski et al.

We propose a reinforcement learning framework for discrete environments in which an agent makes both strategic and tactical decisions. The former manifests itself through the use of value function, while the latter is powered by a tree search planner. These tools complement each other. The planning module performs a local \textit{what-if} analysis, which allows to avoid tactical pitfalls and boost backups of the value function. The value function, being global in nature, compensates for inherent locality of the planner. In order to further solidify this synergy, we introduce an exploration mechanism with two distinctive components: uncertainty modelling and risk measurement. To model the uncertainty we use value function ensembles, and to reflect risk we use propose several functionals that summarize the implied by the ensemble. We show that our method performs well on hard exploration environments: Deep-sea, toy Montezuma's Revenge, and Sokoban. In all the cases, we obtain speed-up in learning and boost in performance.

Lukasz Kaiser, Mohammad Babaeizadeh, Piotr Milos et al.

Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- substantially more, in fact, than a human would need to learn the same games. How can people learn so quickly? Part of the answer may be that people can learn how the game works and predict which actions will lead to desirable outcomes. In this paper, we explore how video prediction models can similarly enable agents to solve Atari games with fewer interactions than model-free methods. We describe Simulated Policy Learning (SimPLe), a complete model-based deep RL algorithm based on video prediction models and present a comparison of several model architectures, including a novel architecture that yields the best results in our setting. Our experiments evaluate SimPLe on a range of Atari games in low data regime of 100k interactions between the agent and the environment, which corresponds to two hours of real-time play. In most games SimPLe outperforms state-of-the-art model-free algorithms, in some games by over an order of magnitude.