Symmetry-Aware Actor-Critic for 3D Molecular Design

Authors: Gregor N. C. Simm, Robert Pinsler, Gábor Csányi, José Miguel Hernández-Lobato

ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We perform experiments to answer the following questions: (1) is the agent able to learn how to build highly symmetric molecules in Cartesian coordinates from scratch, (2) can we increase the validity, diversity, and stability of generated molecules, and (3) does our approach lead to improved generalization?
Researcher Affiliation Academia 1Department of Engineering, University of Cambridge, Cambridge, UK 2Alan Turing Institute, London, UK {gncs2,rp586,gc121,jmh233}@cam.ac.uk
Pseudocode Yes Below, we detail the algorithm of the OPT agent.
Open Source Code Yes Source code of the agent and environment is available at https://github.com/gncs/molgym.
Open Datasets Yes We address (1) and (2) by evaluating the agent on a diverse range of tasks from the MOLGYM benchmark suite (Simm et al., 2020), and (3) on a newly proposed stochastic-bag task (see Section 5.1) where bags are sampled from a distribution over bags.
Dataset Splits No The paper does not explicitly provide details about a distinct validation dataset split for model training or hyperparameter tuning. It mentions 'offline evaluation' which is used for final assessment.
Hardware Specification Yes Experiments were run on an Intel Xeon E5-2650 v4 2.2GHz 12-core processor (96Gi B RAM) and an Nvidia P100 GPU (16Gi B).
Software Dependencies No Our agent is implemented in the deep learning framework Py Torch (Paszke et al., 2019). Data analysis was performed with the Python libraries matplotlib (Hunter, 2007) and pandas (Mc Kinney, 2010). We use the implementation in the software package SPARROW (Husch et al., 2018; Bosia et al., 2020).
Experiment Setup Yes Hyperparameters for CORMORANT are listed in Table 3. Further hyperparameters used in our experiments are in Table 4.