Related papers: Marginal Utility for Planning in Continuous or Lar…

In robotics, it is essential to be able to plan efficiently in high-dimensional continuous state-action spaces for long horizons. For such complex planning problems, unguided uniform sampling of actions until a path to a goal is found is…

A key goal in stochastic contextual linear bandits is to efficiently learn a near-optimal policy. Prior algorithms for this problem learn a policy by strategically sampling actions but naively (passively) sampling contexts from the…

Exploration is critical to a reinforcement learning agent's performance in its given environment. Prior exploration methods are often based on using heuristic auxiliary predictions to guide policy behavior, lacking a mathematically-grounded…

Temporal planning is an extension of classical planning involving concurrent execution of actions and alignment with temporal constraints. Durative actions along with invariants allow for modeling domains in which multiple agents operate in…

Many important real-world problems have action spaces that are high-dimensional, continuous or both, making full enumeration of all possible actions infeasible. Instead, only small subsets of actions can be sampled for the purpose of policy…

The training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment. Nowadays several data sets containing recorded experiences of intelligent agents performing various tasks, spanning…

Strategic classification studies learning in settings where self-interested users can strategically modify their features to obtain favorable predictive outcomes. A key working assumption, however, is that "favorable" always means…

In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while…

Real-world engineering systems are typically compared and contrasted using multiple metrics. For practical machine learning systems, performance tuning is often more nuanced than minimizing a single expected loss objective, and it may be…

Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes made by classifiers, typically turning to dishonest actions when they are less costly…

Simulation-based planning with rollouts is a widely-deployed technique for decision making in stochastic environments. The primary instrument of simulation-based planning is a sampling model, which is repeatedly called to generate…

Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is unknown or cannot easily be used for training. In this work, we empirically examine the effects of domain…

Sampling-based planners are effective in many real-world applications such as robotics manipulation, navigation, and even protein modeling. However, it is often challenging to generate a collision-free path in environments where key areas…

We propose a learning-from-demonstration approach for grounding actions from expert data and an algorithm for using these actions to perform a task in new environments. Our approach is based on an application of sampling-based motion…

Model-based reinforcement learning algorithms are typically more sample efficient than their model-free counterparts, especially in sparse reward problems. Unfortunately, many interesting domains are too complex to specify the complete…

Standard model-free reinforcement learning algorithms optimize a policy that generates the action to be taken in the current time step in order to maximize expected future return. While flexible, it faces difficulties arising from the…

Learning the continuous dynamics of a system from snapshots of its temporal marginals is a problem which appears throughout natural sciences and machine learning, including in quantum systems, single-cell biological data, and generative…

Exploration is a fundamental problem in robotics. While sampling-based planners have shown high performance, they are oftentimes compute intensive and can exhibit high variance. To this end, we propose to directly learn the underlying…

Modern applications and progress in deep learning research have created renewed interest for generative models of text and of images. However, even today it is unclear what objective functions one should use to train and evaluate these…

By planning through a learned dynamics model, model-based reinforcement learning (MBRL) offers the prospect of good performance with little environment interaction. However, it is common in practice for the learned model to be inaccurate,…