arXiv research

ISA learns subgoals for reinforcement learning agents.

Framework learns useful subgoals from demonstrations and instructions.

Paper shows intrinsic motivation boosts exploration efficiency in HRL.

Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects. However, due to the compounding uncertainty in long horizon video prediction and poor s…

Hierarchical Reinforcement Learning (HRL) exploits temporally extended actions, or options, to make decisions from a higher-dimensional perspective to alleviate the sparse reward problem, one of the most challenging problems in reinforcement learning. The majority of existing HRL algorithms require either significant m…

The paper introduces an adjacency constraint to improve goal-conditioned HRL.

Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, s…

A central challenge in reinforcement learning is discovering effective policies for tasks where rewards are sparsely distributed. We postulate that in the absence of useful reward signals, an effective exploration strategy should seek out {\it decision states}. These states lie at critical junctions in the state space …

MGHRL learns to generate high-level meta strategies for new tasks.

Building agents that can explore their environments intelligently is a challenging open problem. In this paper, we make a step towards understanding how a hierarchical design of the agent's policy can affect its exploration capabilities. First, we design EscapeRoom environments, where the agent must figure out how to n…

Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behavior that reflects only a single intention. Instead of learning a global behavioral model, recent IRL methods divide the demonstration data i…

Deep learning optimizes VWAP strategy for lower transaction costs.

This paper presents a way of solving Markov Decision Processes that combines state abstraction and temporal abstraction. Specifically, we combine state aggregation with the options framework and demonstrate that they work well together and indeed it is only after one combines the two that the full benefit of each is re…

HRL4IN tackles interactive navigation tasks with mobile manipulators, improving efficiency and performance.

Paper explores how knowledge distillation transfers inductive biases between models.

Interpolated-MLPs control inductive bias for better performance in low-compute tasks.

New method quantifies inductive bias for machine learning tasks.

One-layer transformers can't solve induction heads task efficiently.

OTI extends OTP for inductive semi-supervised learning.

Strong inductive biases prevent harmless interpolation in overparameterized models.

Deep ResNets favor low bottleneck rank with proper hyperparameters.

This research formalizes inductive generalization and proposes a new learning paradigm called Inductive Learning.

We introduce several methods to define the self-inductance of a single loop as the regularization of divergent integrals which we obtain by applying Neumann (or Weber) formula for the mutual inductance of a pair of loops to the case when two loops are identical.

We introduce the notion of large scale inductive dimension for asymptotic resemblance spaces. We prove that the large scale inductive dimension and the asymptotic dimensiongrad are equal in the class of r-convex metric spaces. This class contains the class of all geodesic metric spaces and all finitely generated groups…

If $p : Y \to X$ is an unramified covering map between two compact oriented surfaces of genus at least two, then it is proved that the embedding map, corresponding to $p$, from the Teichmüller space ${\cal T}(X)$, for $X$, to ${\cal T}(Y)$ actually extends to an embedding between the Thurston compactification of the tw…

Novel framework for Bayesian reinforcement learning infers value function distributions.

Noise affects the effectiveness of interpolating models, especially those with strong inductive biases.

Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversari…

GraIL predicts relations by reasoning over subgraphs, outperforming embeddings.

New approach relaxes inductive biases of physics-inspired NNs for better performance.

Study links neural network inductive bias, feature learning, and generalization on Boolean functions.

Novel approach trains LLMs for inductive reasoning using probabilistic programs.

We prove addition and subspace theorems for asymptotic large inductive dimension. We investigate a transfinite extension of this dimension and show that it is trivial.

Extends positive mass theorem to arbitrary dimensions using a new inductive scheme.

I-BERT extends Transformer's self-attention to arbitrary input lengths.

Transformers learn rich in-context dependencies efficiently.

Novel approach uses inductive biases for semiconductor etching.

Factor complexity $b_φ(n)$ for a vertex coloring $φ$ of a regular tree is the number of colored $n$-balls up to color-preserving automorphisms. Sturmian colorings are colorings of minimal unbounded factor complexity $b_φ(n) = n+2$. In this article, we prove an induction algorithm for Sturmian colorings using colored ba…

Prediction is arguably one of the most basic functions of an intelligent system. In general, the problem of predicting events in the future or between two waypoints is exceedingly difficult. However, most phenomena naturally pass through relatively predictable bottlenecks---while we cannot predict the precise trajector…

Integrates inductive biases into VAEs using intermediary latent variables.

This paper explains the theoretical inductive bias of Isolation Forest.

R2N learns interpretable rules and literals from numerical features.

Machine learning refactors knowledge to improve learning efficiency.

We define and study the Burnside quotient Green ring of a Mackey functor. Some refinements of Dress induction theory are presented, together with applications to computation results for $K$-theory and $L$-theory of finite and infinite groups.

Transformers learn to use induction heads or shortcuts based on data diversity.

We apply Murasugi-Tristram inequality to real algebraic curves of odd degree on $RP^2$ with a deep nest, i.e. a nest of the depth $k-1$ where $2k+1$ is the degree. For such curves, the ingredients of the Murasugi-Tristram inequality can be computed (or estimated) inductively using the computations for iterated torus li…

We propose a Poisson-Lie analog of the symplectic induction procedure, using an appropriate Poisson generalization of the reduction of symplectic manifolds with symmetry. Having as basic tools the equivariant momentum maps of Poisson actions, the double group of a Poisson-Lie group and the reduction of Poisson manifold…

We propose an inductive matrix completion model without using side information. By factorizing the (rating) matrix into the product of low-dimensional latent embeddings of rows (users) and columns (items), a majority of existing matrix completion methods are transductive, since the learned embeddings cannot generalize …