A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New algorithm improves model generalization in structured biomedical domains.
Learning disentangled representations is a key step towards effectively discovering and modelling the underlying structure of environments. In the natural sciences, physics has found great success by describing the universe in terms of symmetry preserving transformations. Inspired by this formalism, we propose a framew…
ISL improves causal structure learning with invariant structures across different environments.
A model is developed to study the effectiveness of innovation and its impact on structure creation and structure change on agent-based societies. The abstract model that is developed is easily adapted to any particular field. In any interacting environment, the agents receive something from the environment (the other a…
The paper formalizes robot environments using topological concepts.
Paper proposes EILLS for invariant linear regression across environments.
ATLAS separates invariant and transferable latent factors across diverse environments.
Study shows tractable generalization in RL is impossible but possible with Strong Proximity.
The paper explores how to apply causal knowledge across different datasets to improve learning.
Two environments are enough to infer causal graphs and counterfactuals.
A structured understanding of our world in terms of objects, relations, and hierarchies is an important component of human cognition. Learning such a structured world model from raw sensory data remains a challenge. As a step towards this goal, we introduce Contrastively-trained Structured World Models (C-SWMs). C-SWMs…
Bayesian model for multi-environment prediction with latent variable changes.
This paper considers the problem of efficient exploration of unseen environments, a key challenge in AI. We propose a `learning to explore' framework where we learn a policy from a distribution of environments. At test time, presented with an unseen environment from the same distribution, the policy aims to generalize …
Complex environments and tasks pose a difficult problem for holistic end-to-end learning approaches. Decomposition of an environment into interacting controllable and non-controllable objects allows supervised learning for non-controllable objects and universal value function approximator learning for controllable obje…
Designs a framework to transfer causal models between similar environments.
This work uses reinforcement learning to optimize task scheduling and execution in a dynamic multi-agent warehouse environment.
Researchers use DT to transfer policies from one environment to another using causal reasoning.
Proposes MSS to identify causal structure from heterogeneous environments.
WILD-SCAV benchmarks AI in complex 3D FPS environments.
Learning transferable knowledge across similar but different settings is a fundamental component of generalized intelligence. In this paper, we approach the transfer learning challenge from a causal theory perspective. Our agent is endowed with two basic yet general theories for transfer learning: (i) a task shares a c…
Perceiving the surrounding environment in terms of objects is useful for any general purpose intelligent agent. In this paper, we investigate a fundamental mechanism making object perception possible, namely the identification of spatio-temporally invariant structures in the sensorimotor experience of an agent. We take…
New method uses unlabeled data to improve model robustness across different environments.
Estimator improves prediction with missing data in multi-environment settings.
Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-s…
Proposes method to learn state abstractions that generalize across environments.
New RL environments help AI learn causal relationships from visual data.
Inverse reinforcement learning has proved its ability to explain state-action trajectories of expert agents by recovering their underlying reward functions in increasingly challenging environments. Recent advances in adversarial learning have allowed extending inverse RL to applications with non-stationary environment …
The paper tackles decision making problems with funnel structure in email marketing campaigns.
The paper uses Bayesian Surprise to identify unexpected structures in indoor environments.
Paper argues context equals environment, improving AI generalization.
Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a learned model of the environment for motion prediction. This modularity explicitly allows for unsupervised adaptation of trajectory prediction models to unseen…
Method identifies unknown intervention targets in structural causal models from diverse data.
Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning. A Bayes-optimal policy, which does so optimally, conditions its actions not only on the environment state but on the agent's uncertainty about the environment. Computing a Bayes-optimal policy is how…
The paper proposes a deep learning technique for structured and composable representations.
Introduces Conditional Action Trees to simplify RL action spaces.
Catastrophic forgetting continues to severely restrict the learnability of controllers suitable for multiple task environments. Efforts to combat catastrophic forgetting reported in the literature to date have focused on how control systems can be updated more rapidly, hastening their adjustment from good initial setti…
This paper explores how environmental properties can simplify reinforcement learning in non-episodic settings.
Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to real world robots to discover repertoires of policies producing a wide diversity of effects. Often th…
FAIR-NN finds invariant variables for causal inference across diverse environments.
ICIL learns policies invariant to multiple environments, improving generalization.
We study causal inference in a multi-environment setting, in which the functional relations for producing the variables from their direct causes remain the same across environments, while the distribution of exogenous noises may vary. We introduce the idea of using the invariance of the functional relations of the vari…
Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target giv…
Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are visually diverse but contain intrinsic semantic regularities. We propose a hybrid …
We propose RecSim, a configurable platform for authoring simulation environments for recommender systems (RSs) that naturally supports sequential interaction with users. RecSim allows the creation of new environments that reflect particular aspects of user behavior and item structure at a level of abstraction well-suit…
New method uses hindsight to make exploration robust in stochastic environments.
Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to perform better in similar future tasks. This paper investigates the counterfactual th…
PFedRL-Rep learns shared and personalized policies for heterogeneous environments.
Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to replicate some of these abilities with a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically …