Search Results for author:
Found 10 papers, 5 papers with code
Predicting Ordinary Differential Equations with Transformers
We develop a transformer-based sequence-to-sequence model that recovers scalar ordinary differential equations (ODEs) in symbolic form from irregularly sampled and noisy observations of a single solution trajectory.
Discovering ordinary differential equations that govern time-series
Natural laws are often described through differential equations yet finding a differential equation that describes the governing law underlying observed data is a challenging and still mostly manual task.
Direct Advantage Estimation
The predominant approach in reinforcement learning is to assign credit to actions based on the expected return.
Neural Symbolic Regression that Scales
We procedurally generate an unbounded set of equations, and simultaneously pre-train a Transformer to predict the symbolic equation from a corresponding set of input-output-pairs.
Learning to interpret trajectories
By learning to predict trajectories of dynamical systems, model-based methods can make extensive use of all observations from past experience.
Divide-and-Conquer Monte Carlo Tree Search
are constrained by an implicit sequential planning assumption: The order in which a plan is constructed is the same in which it is executed.
CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
To facilitate research addressing this problem, we propose CausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation environment.
Learning explanations that are hard to vary
In this paper, we investigate the principle that `good explanations are hard to vary' in the context of deep learning.
Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning
are constrained by an implicit sequential planning assumption: The order in which a plan is constructed is the same in which it is executed.
Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models
We introduce a method which enables a recurrent dynamics model to be temporally abstract.
