Search Results for author:
Found 20 papers, 11 papers with code
Sequence Modeling is a Robust Contender for Offline Reinforcement Learning
Our key findings are: (1) Sequence Modeling requires more data than Q-Learning to learn competitive policies but is more robust; (2) Sequence Modeling is a substantially better choice than both Q-Learning and Imitation Learning in sparse-reward and low-quality data settings; and (3) Sequence Modeling and Imitation Learning are preferable as task horizon increases, or when data is obtained from human demonstrators.
Overcoming the Pitfalls of Prediction Error in Operator Learning for Bilevel Planning
Bilevel planning, in which a high-level search over an abstraction of an environment is used to guide low-level decision-making, is an effective approach to solving long-horizon tasks in continuous state and action spaces.
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.
Towards Optimal Correlational Object Search
In realistic applications of object search, robots will need to locate target objects in complex environments while coping with unreliable sensors, especially for small or hard-to-detect objects.
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.
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.
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.
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).
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.
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.
PDDLGym: Gym Environments from PDDL Problems
We present PDDLGym, a framework that automatically constructs OpenAI Gym environments from PDDL domains and problems.
Intrinsic Motivation for Encouraging Synergistic Behavior
Our key idea is that a good guiding principle for intrinsic motivation in synergistic tasks is to take actions which affect the world in ways that would not be achieved if the agents were acting on their own.
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.
Learning Compact Models for Planning with Exogenous Processes
We address the problem of approximate model minimization for MDPs in which the state is partitioned into endogenous and (much larger) exogenous components.
Efficient Bimanual Manipulation Using Learned Task Schemas
Our insight is that for many tasks, the learning process can be decomposed into learning a state-independent task schema (a sequence of skills to execute) and a policy to choose the parameterizations of the skills in a state-dependent manner.
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 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.
Finding Frequent Entities in Continuous Data
In many applications that involve processing high-dimensional data, it is important to identify a small set of entities that account for a significant fraction of detections.
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.
