104 citations · 374 across the 40 of their papers we have counts for
7 papers · 2 filters
An Information-Geometric Distance on the Space of Tasks
Yansong Gao, Pratik Chaudhari
This paper prescribes a distance between learning tasks modeled as joint distributions on data and labels. Using tools in information geometry, the distance is defined to be the le…
Proximal Deterministic Policy Gradient
Marco Maggipinto, Gian Antonio Susto, Pratik Chaudhari
This paper introduces two simple techniques to improve off-policy Reinforcement Learning (RL) algorithms. First, we formulate off-policy RL as a stochastic proximal point iteration…
MIDAS: Multi-agent Interaction-aware Decision-making with Adaptive Strategies for Urban Autonomous Navigation
Xiaoyi Chen, Pratik Chaudhari
Autonomous navigation in crowded, complex urban environments requires interacting with other agents on the road. A common solution to this problem is to use a prediction model to g…
DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning
Rasool Fakoor, Pratik Chaudhari, Alexander J. Smola
This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity. First, we show that simp…
Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation
Rasool Fakoor, Jonas Mueller, Nick Erickson +2
Automated machine learning (AutoML) can produce complex model ensembles by stacking, bagging, and boosting many individual models like trees, deep networks, and nearest neighbor es…
TraDE: Transformers for Density Estimation
Rasool Fakoor, Pratik Chaudhari, Jonas Mueller +1
We present TraDE, a self-attention-based architecture for auto-regressive density estimation with continuous and discrete valued data. Our model is trained using a penalized maximu…
A Free-Energy Principle for Representation Learning
Yansong Gao, Pratik Chaudhari
This paper employs a formal connection of machine learning with thermodynamics to characterize the quality of learnt representations for transfer learning. We discuss how informati…