Related papers: Planning by Prioritized Sweeping with Small Backup…
Reservoir computing is a recently introduced machine learning paradigm that has been shown to be well-suited for the processing of spatiotemporal data. Rather than training the network node connections and weights via backpropagation in…
We present a planner for large-scale (un)labeled object sorting tasks, which uses two types of manipulation actions: overhead grasping and planar pushing. The grasping action offers completeness guarantee under mild assumptions, and planar…
In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model. In this work, we present a novel, training-free approach to improving the performance of such agents separately from…
We are interested in how to design reinforcement learning agents that provably reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones. The availability of solutions to related problems…
This paper addresses non-prehensile rearrangement planning problems where a robot is tasked to rearrange objects among obstacles on a planar surface. We present an efficient planning algorithm that is designed to impose few assumptions on…
Designing effective model-based reinforcement learning algorithms is difficult because the ease of data generation must be weighed against the bias of model-generated data. In this paper, we study the role of model usage in policy…
Procedural planning, which entails decomposing a high-level goal into a sequence of temporally ordered steps, is an important yet intricate task for machines. It involves integrating common-sense knowledge to reason about complex and often…
In Reinforcement Learning, the trade-off between exploration and exploitation poses a complex challenge for achieving efficient learning from limited samples. While recent works have been effective in leveraging past experiences for policy…
Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning (RL), primarily in the form of distillation or auxiliary…
Model-based Bayesian reinforcement learning has generated significant interest in the AI community as it provides an elegant solution to the optimal exploration-exploitation tradeoff in classical reinforcement learning. Unfortunately, the…
Existing Reinforcement Learning (RL) systems encounter significant challenges when applied to real-world scenarios, primarily due to poor generalization across environments that differ from their training conditions. This thesis explores…
Large-scale Markov decision processes (MDPs) require planning algorithms with runtime independent of the number of states of the MDP. We consider the planning problem in MDPs using linear value function approximation with only weak…
We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs). Our approach uses dynamic programming to balance a trade-off between caching of…
In reinforcement learning, experience replay stores past samples for further reuse. Prioritized sampling is a promising technique to better utilize these samples. Previous criteria of prioritization include TD error, recentness and…
The solution convergence of Markov Decision Processes (MDPs) can be accelerated by prioritized sweeping of states ranked by their potential impacts to other states. In this paper, we present new heuristics to speed up the solution…
As machine learning tasks continue to evolve, the trend has been to gather larger datasets and train increasingly larger models. While this has led to advancements in accuracy, it has also escalated computational costs to unsustainable…
Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern when seeking to deploy very deep architectures in production,…
Motion planning is an essential component in most of today's robotic applications. In this work, we consider the learning setting, where a set of solved motion planning problems is used to improve the efficiency of motion planning on…
The history of learning for control has been an exciting back and forth between two broad classes of algorithms: planning and reinforcement learning. Planning algorithms effectively reason over long horizons, but assume access to a local…
We study prediction of future outcomes with supervised models that use privileged information during learning. The privileged information comprises samples of time series observed between the baseline time of prediction and the future…