Search Results for author:
Found 11 papers, 5 papers with code
Planning in a recurrent neural network that plays Sokoban
How a neural network (NN) generalizes to novel situations depends on whether it has learned to select actions heuristically or via a planning process.
SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking
This allows us to minimize a variety of divergences between the distribution of sequences generated by an autoregressive model and sequences from a dataset, including divergences with weight on OOD generated sequences.
On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence
In this work, we explore the promises and challenges of developing multimodal foundation models for GeoAI.
LMPriors: Pre-Trained Language Models as Task-Specific Priors
Particularly in low-data regimes, an outstanding challenge in machine learning is developing principled techniques for augmenting our models with suitable priors.
Beyond Bayes-optimality: meta-learning what you know you don't know
This is in contrast to risk-sensitive agents, which additionally exploit the higher-order moments of the return, and ambiguity-sensitive agents, which act differently when recognizing situations in which they lack knowledge.
Neural Networks and the Chomsky Hierarchy
Reliable generalization lies at the heart of safe ML and AI.
BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery
We propose Bayesian Causal Discovery Nets (BCD Nets), a variational inference framework for estimating a distribution over DAGs characterizing a linear-Gaussian SEM.
IQ-Learn: Inverse soft-Q Learning for Imitation
In many sequential decision-making problems (e. g., robotics control, game playing, sequential prediction), human or expert data is available containing useful information about the task.
Ranked #1 on
MuJoCo Games
on Walker2d
Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients
We consider the task of training a policy that maximizes reward while minimizing disclosure of certain sensitive state variables through the actions.
Exploring Hierarchy-Aware Inverse Reinforcement Learning
We introduce a new generative model for human planning under the Bayesian Inverse Reinforcement Learning (BIRL) framework which takes into account the fact that humans often plan using hierarchical strategies.
Parallelizing Linear Recurrent Neural Nets Over Sequence Length
Recurrent neural networks (RNNs) are widely used to model sequential data but their non-linear dependencies between sequence elements prevent parallelizing training over sequence length.
