AtomComposer uses online RL with multi-composition training to discover up to 10x more valid 3D isomers on unseen chemical formulas than single-composition baselines.
Mankowitz, Jerry Li, Cosmin Paduraru, Sven Gowal, and Todd Hes- ter
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
D4RL supplies new offline RL benchmarks and datasets from expert and mixed sources to expose weaknesses in existing algorithms and standardize evaluation.
SV-DRO evolves parameter particles via task-optimality-gap Stein gradients inside DRO-MPC, yielding up to 3× higher success on contact-rich manipulation under parametric uncertainty.
RepMT-SAC uses spectral MDP decomposition to build a task-agnostic value-function core plus minimal task adjustment, yielding up to 30% better performance than baselines on quadcopter trajectory tasks with zero-shot in-distribution and few-shot out-of-distribution transfer.
citing papers explorer
-
AtomComposer: Discovering Chemical Space from First Principles with Reinforcement Learning
AtomComposer uses online RL with multi-composition training to discover up to 10x more valid 3D isomers on unseen chemical formulas than single-composition baselines.
-
D4RL: Datasets for Deep Data-Driven Reinforcement Learning
D4RL supplies new offline RL benchmarks and datasets from expert and mixed sources to expose weaknesses in existing algorithms and standardize evaluation.
-
Distributionally Robust Control via Stein Variational Inference for Contact-Rich Manipulation
SV-DRO evolves parameter particles via task-optimality-gap Stein gradients inside DRO-MPC, yielding up to 3× higher success on contact-rich manipulation under parametric uncertainty.
-
Learning to Adapt: Representation-Based Reinforcement Learning for Multi-Task Skill Transfer
RepMT-SAC uses spectral MDP decomposition to build a task-agnostic value-function core plus minimal task adjustment, yielding up to 30% better performance than baselines on quadcopter trajectory tasks with zero-shot in-distribution and few-shot out-of-distribution transfer.