Search Results for author:
Found 66 papers, 24 papers with code
Learning to Cooperate via Policy Search
Cooperative games are those in which both agents share the same payoff structure.
Object-based World Modeling in Semi-Static Environments with Dependent Dirichlet-Process Mixtures
We refer to this attribute-based representation as a world model, and consider how to acquire it via noisy perception and maintain it over time, as objects are added, changed, and removed in the world.
Bayesian Optimization with Exponential Convergence
This paper presents a Bayesian optimization method with exponential convergence without the need of auxiliary optimization and without the delta-cover sampling.
Backward-Forward Search for Manipulation Planning
In this paper we address planning problems in high-dimensional hybrid configuration spaces, with a particular focus on manipulation planning problems involving many objects.
Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems
We introduce a framework for model learning and planning in stochastic domains with continuous state and action spaces and non-Gaussian transition models.
Learning to Rank for Synthesizing Planning Heuristics
We investigate learning heuristics for domain-specific planning.
STRIPS Planning in Infinite Domains
We introduce STRIPStream: an extension of the STRIPS language which can model these domains by supporting the specification of blackbox generators to handle complex constraints.
Generalization in Deep Learning
This paper provides theoretical insights into why and how deep learning can generalize well, despite its large capacity, complexity, possible algorithmic instability, nonrobustness, and sharp minima, responding to an open question in the literature.
Guiding the search in continuous state-action spaces by learning an action sampling distribution from off-target samples
For such complex planning problems, unguided uniform sampling of actions until a path to a goal is found is hopelessly inefficient, and gradient-based approaches often fall short when the optimization manifold of a given problem is not smooth.
Selecting Representative Examples for Program Synthesis
Program synthesis is a class of regression problems where one seeks a solution, in the form of a source-code program, mapping the inputs to their corresponding outputs exactly.
Learning to select examples for program synthesis
In this paper we address this challenge by constructing a representative subset of examples that is both small and is able to constrain the solver sufficiently.
Generalization in Machine Learning via Analytical Learning Theory
This paper introduces a novel measure-theoretic theory for machine learning that does not require statistical assumptions.
PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning
We extend PDDL to support a generic, declarative specification for these procedures that treats their implementation as black boxes.
Integrating Human-Provided Information Into Belief State Representation Using Dynamic Factorization
In partially observed environments, it can be useful for a human to provide the robot with declarative information that represents probabilistic relational constraints on properties of objects in the world, augmenting the robot's sensory observations.
Active model learning and diverse action sampling for task and motion planning
Solving long-horizon problems in complex domains requires flexible generative planning that can combine primitive abilities in novel combinations to solve problems as they arise in the world.
Learning What Information to Give in Partially Observed Domains
We consider such a setting in which the agent can, while acting, transmit declarative information to the human that helps them understand aspects of this unseen environment.
Learning to guide task and motion planning using score-space representation
In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems.
Learning Quickly to Plan Quickly Using Modular Meta-Learning
Multi-object manipulation problems in continuous state and action spaces can be solved by planners that search over sampled values for the continuous parameters of operators.
Learning sparse relational transition models
For any action, a rule selects a set of relevant objects and computes a distribution over properties of just those objects in the resulting state given their properties in the previous state.
Effect of Depth and Width on Local Minima in Deep Learning
In this paper, we analyze the effects of depth and width on the quality of local minima, without strong over-parameterization and simplification assumptions in the literature.
Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior
Bayesian optimization usually assumes that a Bayesian prior is given.
Elimination of All Bad Local Minima in Deep Learning
At every local minimum of any deep neural network with these added neurons, the set of parameters of the original neural network (without added neurons) is guaranteed to be a global minimum of the original neural network.
Every Local Minimum Value is the Global Minimum Value of Induced Model in Non-convex Machine Learning
Furthermore, as special cases of our general results, this article improves or complements several state-of-the-art theoretical results on deep neural networks, deep residual networks, and overparameterized deep neural networks with a unified proof technique and novel geometric insights.
Few-Shot Bayesian Imitation Learning with Logical Program Policies
We propose an expressive class of policies, a strong but general prior, and a learning algorithm that, together, can learn interesting policies from very few examples.
Graph Element Networks: adaptive, structured computation and memory
We explore the use of graph neural networks (GNNs) to model spatial processes in which there is no a priori graphical structure.
Differentiable Algorithm Networks for Composable Robot Learning
This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems.
Online Replanning in Belief Space for Partially Observable Task and Motion Problems
To solve multi-step manipulation tasks in the real world, an autonomous robot must take actions to observe its environment and react to unexpected observations.
GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal Babbling
We address the problem of efficient exploration for transition model learning in the relational model-based reinforcement learning setting without extrinsic goals or rewards.
Meta-learning curiosity algorithms
We hypothesize that curiosity is a mechanism found by evolution that encourages meaningful exploration early in an agent's life in order to expose it to experiences that enable it to obtain high rewards over the course of its lifetime.
Visual Prediction of Priors for Articulated Object Interaction
Given a novel object, the objective is to maximize reward with few interactions.
Learning compositional models of robot skills for task and motion planning
We use, and develop novel improvements on, state-of-the-art methods for active learning and sampling.
CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs
A general meta-planning strategy is to learn to impose constraints on the states considered and actions taken by the agent.
Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks
We conclude that learning to predict a sufficient set of objects for a planning problem is a simple, powerful, and general mechanism for planning in large instances.
Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
Adding auxiliary losses to the main objective function is a general way of encoding biases that can help networks learn better representations.
Learning Online Data Association
When an agent interacts with a complex environment, it receives a stream of percepts in which it may detect entities, such as objects or people.
Integrated Task and Motion Planning
The problem of planning for a robot that operates in environments containing a large number of objects, taking actions to move itself through the world as well as to change the state of the objects, is known as task and motion planning (TAMP).
Measuring few-shot extrapolation with program induction
Program induction lies at the opposite end of the spectrum: programs are capable of extrapolating from very few examples, but we still do not know how to efficiently search for complex programs.
Temporal and Object Quantification Nets
We aim to learn generalizable representations for complex activities by quantifying over both entities and time, as in “the kicker is behind all the other players,” or “the player controls the ball until it moves toward the goal.” Such a structural inductive bias of object relations, object quantification, and temporal orders will enable the learned representation to generalize to situations with varying numbers of agents, objects, and time courses.
Learning Symbolic Operators for Task and Motion Planning
We then propose a bottom-up relational learning method for operator learning and show how the learned operators can be used for planning in a TAMP system.
Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning
In robotic domains, learning and planning are complicated by continuous state spaces, continuous action spaces, and long task horizons.
Temporal and Object Quantification Networks
We present Temporal and Object Quantification Networks (TOQ-Nets), a new class of neuro-symbolic networks with a structural bias that enables them to learn to recognize complex relational-temporal events.
Long-Horizon Manipulation of Unknown Objects via Task and Motion Planning with Estimated Affordances
We present a strategy for designing and building very general robot manipulation systems involving the integration of a general-purpose task-and-motion planner with engineered and learned perception modules that estimate properties and affordances of unknown objects.
Learning Rational Skills for Planning from Demonstrations and Instructions
We present a framework for learning compositional, rational skill models (RatSkills) that support efficient planning and inverse planning for achieving novel goals and recognizing activities.
On the Expressiveness and Learning of Relational Neural Networks on Hypergraphs
Our first contribution is a fine-grained analysis of the expressiveness of these neural networks, that is, the set of functions that they can realize and the set of problems that they can solve.
Efficient Training and Inference of Hypergraph Reasoning Networks
To leverage the sparsity in hypergraph neural networks, SpaLoc represents the grounding of relationships such as parent and grandparent as sparse tensors and uses neural networks and finite-domain quantification operations to infer new facts based on the input.
Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators
In this paper, we propose to leverage domain-independent heuristic functions commonly used in the classical planning literature to improve the sample efficiency of RL.
Representation, learning, and planning algorithms for geometric task and motion planning
The first is an algorithm for learning a rank function that guides the discrete task level search, and the second is an algorithm for learning a sampler that guides the continuous motionlevel search.
Predicate Invention for Bilevel Planning
Our key idea is to learn predicates by optimizing a surrogate objective that is tractable but faithful to our real efficient-planning objective.
PG3: Policy-Guided Planning for Generalized Policy Generation
In this work, we study generalized policy search-based methods with a focus on the score function used to guide the search over policies.
Learning Neuro-Symbolic Skills for Bilevel Planning
Decision-making is challenging in robotics environments with continuous object-centric states, continuous actions, long horizons, and sparse feedback.
Learning Efficient Abstract Planning Models that Choose What to Predict
An effective approach to solving long-horizon tasks in robotics domains with continuous state and action spaces is bilevel planning, wherein a high-level search over an abstraction of an environment is used to guide low-level decision-making.
SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields
This formalism is implemented in three steps: assigning a consistent local coordinate frame to the task-relevant object parts, determining the location and orientation of this coordinate frame on unseen object instances, and executing an action that brings these frames into the desired alignment.
On the Expressiveness and Generalization of Hypergraph Neural Networks
Next, we analyze the learning properties of these neural networks, especially focusing on how they can be trained on a finite set of small graphs and generalize to larger graphs, which we term structural generalization.
PDSketch: Integrated Planning Domain Programming and Learning
This paper studies a model learning and online planning approach towards building flexible and general robots.
Sparse and Local Networks for Hypergraph Reasoning
Reasoning about the relationships between entities from input facts (e. g., whether Ari is a grandparent of Charlie) generally requires explicit consideration of other entities that are not mentioned in the query (e. g., the parents of Charlie).
Learning Rational Subgoals from Demonstrations and Instructions
We present a framework for learning useful subgoals that support efficient long-term planning to achieve novel goals.
Generalized Planning in PDDL Domains with Pretrained Large Language Models
We investigate whether LLMs can serve as generalized planners: given a domain and training tasks, generate a program that efficiently produces plans for other tasks in the domain.
DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability
Task and Motion Planning (TAMP) approaches are effective at planning long-horizon autonomous robot manipulation.
Embodied Lifelong Learning for Task and Motion Planning
A robot deployed in a home over long stretches of time faces a true lifelong learning problem.
Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization.
Compositional Diffusion-Based Continuous Constraint Solvers
This paper introduces an approach for learning to solve continuous constraint satisfaction problems (CCSP) in robotic reasoning and planning.
Neural Relational Inference with Fast Modular Meta-learning
Framing inference as the inner-loop optimization of meta-learning leads to a model-based approach that is more data-efficient and capable of estimating the state of entities that we do not observe directly, but whose existence can be inferred from their effect on observed entities.
Learning Reusable Manipulation Strategies
Humans demonstrate an impressive ability to acquire and generalize manipulation "tricks."
What Planning Problems Can A Relational Neural Network Solve?
Goal-conditioned policies are generally understood to be "feed-forward" circuits, in the form of neural networks that map from the current state and the goal specification to the next action to take.
Practice Makes Perfect: Planning to Learn Skill Parameter Policies
We consider a setting where a robot is initially equipped with (1) a library of parameterized skills, (2) an AI planner for sequencing together the skills given a goal, and (3) a very general prior distribution for selecting skill parameters.
Partially Observable Task and Motion Planning with Uncertainty and Risk Awareness
We propose a strategy for TAMP with Uncertainty and Risk Awareness (TAMPURA) that is capable of efficiently solving long-horizon planning problems with initial-state and action outcome uncertainty, including problems that require information gathering and avoiding undesirable and irreversible outcomes.
