Sample Efficient Ensemble Learning with Catalyst.RL
We present Catalyst.RL, an open-source PyTorch framework for reproducible and sample efficient reinforcement learning (RL) research. Main features of Catalyst.RL include large-scale asynchronous distributed training, efficient implementations of various RL algorithms and auxiliary tricks, such as n-step returns, value distributions, hyperbolic reinforcement learning, etc. To demonstrate the effectiveness of Catalyst.RL, we applied it to a physics-based reinforcement learning challenge "NeurIPS 2019: Learn to Move -- Walk Around" with the objective to build a locomotion controller for a human musculoskeletal model. The environment is computationally expensive, has a high-dimensional continuous action space and is stochastic. Our team took the 2nd place, capitalizing on the ability of Catalyst.RL to train high-quality and sample-efficient RL agents in only a few hours of training time. The implementation along with experiments is open-sourced so results can be reproduced and novel ideas tried out.
Code (2)
Tasks
Ensemble Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Predicting the hydrogen release ability of LiBH4-based mixtures by ensemble machine learning
The prediction of hydrogen release ability is indispensable to evaluating hydrogen storage performance of LiBH4-based mixtures before experimentation. To achieve this goal, ensemble machine learning is employed to au…
Transition States Energies from Machine Learning: An Application to Reverse Water-Gas Shift on Single-Atom Alloys
Obtaining accurate transition state (TS) energies is a bottleneck in computational screening of complex materials and reaction networks due to the high cost of TS search methods and first-principles methods such as densi…
GPRInterpretable epistemic uncertainty decomposition in sequential generative models via polynomial chaos surrogates
Sequential generative models conditioned on uncertain rewards are central to AI-driven scientific discovery, yet the epistemic uncertainty they inherit from imperfect reward estimates remains unquantified. We propagate t…
Quantitative Prediction on the Enantioselectivity of Multiple Chiral Iodoarene Scaffolds Based on Whole Geometry
The mechanistic underpinnings of asymmetric catalysis at atomic levels provide shortcuts for developing the potential value of chiral catalysts beyond the current state-of-the-art. In the enantioselective redox transform…
Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks
Molecular Representation Learning (MRL) has proven impactful in numerous biochemical applications such as drug discovery and enzyme design. While Graph Neural Networks (GNNs) are effective at learning molecular represent…
Drug DiscoveryEnsemble Learningmolecular representationRepresentation Learning