Search Results for author:
Found 21 papers, 8 papers with code
EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning
To tackle these issues, in this paper, we present EXPLORER which is an exploration-guided reasoning agent for textual reinforcement learning.
Compositional Program Generation for Few-Shot Systematic Generalization
Compositional generalization is a key ability of humans that enables us to learn new concepts from only a handful examples.
Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing
Nearly all general-purpose neural semantic parsers generate logical forms in a strictly top-down autoregressive fashion.
Learning in Factored Domains with Information-Constrained Visual Representations
This raises the question of how humans learn to efficiently represent visual information in a manner useful for learning tasks.
Compositional generalization through abstract representations in human and artificial neural networks
Our findings give empirical support to the role of compositional generalization in human behavior, implicate abstract representations as its neural implementation, and illustrate that these representations can be embedded into ANNs by designing simple and efficient pretraining procedures.
Hierarchical Reinforcement Learning with AI Planning Models
Our approach defines options in hierarchical reinforcement learning (HRL) from AIP operators by establishing a correspondence between the state transition model of AI planning problem and the abstract state transition system of a Markov Decision Process (MDP).
A Hybrid Neuro-Symbolic approach for Text-Based Games using Inductive Logic Programming
These rules are learned in an online manner and applied with an ASP solver to predict an action for the agent.
Inductive logic programming
Natural Language Understanding
+2
Consolidation via Policy Information Regularization in Deep RL for Multi-Agent Games
This paper introduces an information-theoretic constraint on learned policy complexity in the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm.
Deep RL With Information Constrained Policies: Generalization in Continuous Control
We focus on the model-free reinforcement learning (RL) setting and formalize our approach in terms of an information-theoretic constraint on the complexity of learned policies.
A Study of Compositional Generalization in Neural Models
One difficulty in the development of such models is the lack of benchmarks with clear compositional and relational task structure on which to systematically evaluate them.
Efficient Black-Box Planning Using Macro-Actions with Focused Effects
Focused macros dramatically improve black-box planning efficiency across a wide range of planning domains, sometimes beating even state-of-the-art planners with access to a full domain model.
CAPACITY-LIMITED REINFORCEMENT LEARNING: APPLICATIONS IN DEEP ACTOR-CRITIC METHODS FOR CONTINUOUS CONTROL
We formalize this type of bounded rationality in terms of an information-theoretic constraint on the complexity of policies that agents seek to learn.
Recursive Routing Networks: Learning to Compose Modules for Language Understanding
The model jointly optimizes the parameters of the functions and the meta-learner{'}s policy for routing inputs through those functions.
Routing Networks and the Challenges of Modular and Compositional Computation
Compositionality is a key strategy for addressing combinatorial complexity and the curse of dimensionality.
Logical Rule Induction and Theory Learning Using Neural Theorem Proving
Our approach is neuro-symbolic in the sense that the rule pred- icates and core facts are given dense vector representations.
Scalable Recollections for Continual Lifelong Learning
Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings.
Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
We propose two methods, namely, strength-based re-ranking and coverage-based re-ranking, to make use of the aggregated evidence from different passages to better determine the answer.
Ranked #1 on
Open-Domain Question Answering
on Quasar
Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning
A routing network is a kind of self-organizing neural network consisting of two components: a router and a set of one or more function blocks.
R$^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
Second, we propose a novel method that jointly trains the Ranker along with an answer-generation Reader model, based on reinforcement learning.
Ranked #4 on
Open-Domain Question Answering
on Quasar
e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations
In this paper we present a new dataset and user simulator e-QRAQ (explainable Query, Reason, and Answer Question) which tests an Agent's ability to read an ambiguous text; ask questions until it can answer a challenge question; and explain the reasoning behind its questions and answer.
Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a sequence of natural language tokens.
Ranked #1 on
Dialogue Generation
on Ubuntu Dialogue (Activity)
