New algorithm improves model generalization in structured biomedical domains.
problem Improving model generalization in structured biomedical domains.
method Proposes a new regret minimization (RGM) algorithm and its structured extension for better performance in diverse environments.
result Significantly outperforms previous state-of-the-art baselines on molecular property prediction, protein homology, and stability prediction.
A framework for learning disentangled representations of symmetric environments.
problem Discovering and modelling the underlying structure of environments.
method Group representation theory for disentangled representations of dynamical environments.
result Our method enables accurate long-horizon predictions and correlates with disentanglement quality.
ISL improves causal structure learning with invariant structures across different environments.
problem Improving causal structure discovery for better generalization and explainability.
method ISL splits data into environments, learns invariant structures, and selects optimal classifiers based on graph structures.
result ISL accurately discovers causal structures and outperforms alternative methods on synthetic and real-world datasets.
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.
problem Determining indistinguishable environments for robots.
method Formalizing robot systems as topological dynamical systems, using covering maps and bisimulation.
result Covering maps can witness indistinguishability of environments under general conditions.
Paper proposes EILLS for invariant linear regression across environments.
problem Estimating true parameter and important variable set in multi-environment settings.
method Environment invariant linear least squares (EILLS) objective function.
result EILLS estimator achieves variable selection consistency and efficient estimation.
ATLAS separates invariant and transferable latent factors across diverse environments.
problem Transfer learning and robust prediction in heterogeneous environments.
method ATLAS leverages invariance principle to disentangle latent factors and uses auxiliary labels for robust prediction.
result Near-oracle performance and robust transferable prediction in new environments.
Study shows tractable generalization in RL is impossible but possible with Strong Proximity.
problem RL agents struggle to generalize to new environments.
method Introduced Weak and Strong Proximity conditions to capture similarity between environments.
result Proved Strong Proximity is sufficient for efficient generalization.
The paper explores how to apply causal knowledge across different datasets to improve learning.
problem How to apply causal knowledge across different datasets to improve learning.
method Investigates the structural causal bandit with transportability, fusing priors from source environments to enhance learning in the deployment setting.
result Achieves a sub-linear regret bound with an explicit dependence on informativeness of prior data, potentially outperforming standard bandit approaches.
Two environments are enough to infer causal graphs and counterfactuals.
problem Inferring causal relations from multiple environments, especially for nonlinear mechanisms.
method Using structural causal models and the invariance principle, the study shows that only two auxiliary environments are sufficient for causal graph inference and counterfactual inference.
result Two auxiliary environments are sufficient for identifying 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.
problem Prediction in environments with changing latent variable distributions.
method Bayesian model with empirical Bayes prior and amortized variational algorithm.
result Method outperforms previous approaches in new environments.
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.
problem Transferability of causal models between different but similar environments.
method Object-oriented representations and continuous optimization for structure learning.
result Demonstrates advantages in gridworld settings using reinforcement learning.
This work uses reinforcement learning to optimize task scheduling and execution in a dynamic multi-agent warehouse environment.
problem Optimizing task scheduling and execution in a dynamic multi-agent warehouse environment with limited observability.
method Deep reinforcement learning to solve both high-level scheduling and low-level multi-agent execution problems.
result Demonstrates the effectiveness of reinforcement learning in optimizing task scheduling and execution in a dynamic multi-agent environment.
Researchers use DT to transfer policies from one environment to another using causal reasoning.
problem Adapting to changes in environmental dynamics in reinforcement learning.
method Applying causal counterfactual reasoning to Decision Transformer (DT) architecture for policy transfer.
result DT successfully transfers a learned policy to new environments while retaining most of the reward.
Proposes MSS to identify causal structure from heterogeneous environments.
problem Distribution shifts between environments violate i.i.d. data assumption.
method Sparse mechanism shift hypothesis, score-based approach.
result Identifies entire causal structure with high probability.
WILD-SCAV benchmarks AI in complex 3D FPS environments.
problem Lack of complexity and diversity in RL environments.
method Developed a 3D open-world FPS game environment.
result Demonstrates effectiveness in benchmarking RL algorithms.
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.
problem Learning robust models for new, unseen environments when labeled data are scarce.
method Regularizes model sensitivity to perturbations in covariate means and covariances without requiring labels.
result Empirically validated on physical and physiological datasets, demonstrating improved robustness.
Estimator improves prediction with missing data in multi-environment settings.
problem Handling missing data in multi-environment settings for robust prediction.
method Derive an estimator from invariance objective under missing outcomes.
result The estimator achieves lower prediction error despite using a biased imputation model.
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.
problem Learning abstractions that generalize in block MDPs.
method Invariant causal prediction to learn model-irrelevant state abstractions (MISA).
result Proves high probability of outputting a state abstraction corresponding to causal feature set for return.
New RL environments help AI learn causal relationships from visual data.
problem Learning causal relationships from visual data for AI agents.
method Designing benchmark RL environments and evaluating representation learning algorithms.
result Explicitly incorporating structure and modularity improves causal induction in model-based RL.
The paper tackles decision making problems with funnel structure in email marketing campaigns.
problem Decision making challenges in systems with funnel structure, where fewer observations are received from deeper layers.
method Formulated as a contextual bandit with funnel structure and developed a multi-task learning algorithm.
result Our algorithms offer significant improvement over previous methods in email marketing campaigns.
The paper uses Bayesian Surprise to identify unexpected structures in indoor environments.
problem Identifying unexpected structures in indoor environments.
method Bayesian Surprise applied to Isovist Analysis of 2D floor plans.
result Surprise regions in indoor environments can be used to focus on important areas in LBS.
Paper argues context equals environment, improving AI generalization.
problem AI models struggle to generalize in new environments.
method In-Context Risk Minimization (ICRM) algorithm.
result ICRM leads to significant out-of-distribution performance improvements.
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.
problem Identifying unknown intervention targets in structural causal models from heterogeneous data.
method Two-phase approach: first recovers exogenous noises, second matches with endogenous variables.
result Proposed method uniquely identifies intervention targets under causal sufficiency assumption.
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.
problem Learning structured and composable representations from input images and discrete labels.
method End-to-end deep learning to learn representations based on distance estimates between class label and contextual information.
result The representations have a clear structure allowing for class and environment decomposition.
Adversarial RL recovers agent rewards from financial market data simulations.
problem Recovering agent rewards in volatile financial markets with unknown dynamics.
method Adversarial inverse reinforcement learning in latent space simulations.
result Adversarial RL can robustly recover agent rewards from latent space representations of real market data.
Introduces Conditional Action Trees to simplify RL action spaces.
problem Challenges in RL with large, complex action spaces.
method Structures action spaces and reduces complexity through Conditional Action Trees.
result Demonstrates effectiveness in reducing action space and improving decision making.
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.
problem Challenges in reinforcement learning with continuous interaction and sparse delayed rewards.
method Analysis of environment shaping and dynamism properties to simplify learning.
result Properties like environment shaping and dynamism can significantly ease learning in non-episodic, sparse reward 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.
problem Nonparametric invariance and causal learning in regression models with varying joint distributions.
method FAIR-NN framework using adversarial optimization and neural networks.
result FAIR-NN identifies invariant variables and quasi-causal variables under minimal conditions.
ICIL learns policies invariant to multiple environments, improving generalization.
problem Learning policies from multiple environments leads to spurious correlations.
method ICIL learns invariant feature representations and a matching imitation policy.
result ICIL policies generalize better to unseen environments.
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.
problem Exploration in sparse-reward or reward-free environments, especially in stochastic settings.
method Learn representations of the future that capture unpredictable aspects, using them to predict and reward only the predictable parts of the world.
result Improves exploration in Atari games and Montezuma's Revenge, robust to stochasticity.
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.
problem Poor performance of single policy in heterogeneous environments.
method Develops PFedRL-Rep framework with shared feature representation and personalized weights.
result Proves linear convergence speedup with respect to the number of agents.
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 …