GIB improves neural network generalization by dynamically selecting task-relevant features across different sequential environments.
problem Poor generalization of deep neural networks to unseen environments.
method Proposes a gated information bottleneck (GIB) approach that dynamically drops spurious correlations and selects task-relevant features.
result GIB outperforms other IB approaches in adversarial robustness and OOD detection.
Diffusion models mimic human actions in sequential tasks.
problem Cloning human behavior in dynamic environments is challenging.
method Adapting diffusion models to handle stochastic, multimodal, and correlated actions.
result Diffusion models closely replicate human behavior in robotic and gaming tasks.
This thesis improves OCO algorithms for dynamic data environments.
problem Sequential, changing data in big data environments.
method Designing algorithms to adapt to changing environments.
result Improved algorithms for online resource allocation.
An agent explores indefinitely in an environment with unlimited rewards.
problem Balancing exploration and exploitation in environments with unlimited rewards.
method Simple example of an environment with unbounded rewards and optimal agent behavior.
result An optimal agent always explores to maximize rewards, regardless of accumulated knowledge.
We describe theoretical bounds and a practical algorithm for teaching a model by demonstration in a sequential decision making environment. Unlike previous efforts that have optimized learners that watch a teacher demonstrate a static policy, we focus on the teacher as a decision maker who can dynamically choose differ…
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 approach transfers rewards learned in one environment to reinforcement learning in a new environment.
problem Transfer of rewards learned using inverse reinforcement learning from one environment to a new, different environment.
method Formulate the problem as a joint system of Bellman equations, develop minimax estimators for the target soft-q-function, solve the source and target system of equations jointly. result The coupled approach removes the first-order influence of source Bellman residual error compared to the sequential approach.
CriticSMC improves planning efficiency in constrained environments.
problem Planning with hard constraints in dynamic environments.
method Sequential Monte Carlo with learned heuristic factors.
result CriticSMC reduces collision rates with low computational cost.
AAMDRL uses DRL to manage assets in noisy, changing environments.
problem Learning in noisy, self-adapting environments with sequential data.
method Augmented state information, one-period lag, walk forward analysis.
result AAMDRL outperforms traditional methods in asset management.
Improved distributed learning with reduced communication costs.
problem Efficient communication in resource-constrained environments for distributed learning.
method Proposed a cost-effective partial communication protocol.
result Communication cost is reduced to O(logT), improving significantly on full communication. Data-driven model selection reduces regret in sequential decisions.
problem Optimizing model selection in stochastic environments with bandit feedback.
method Data-driven regret balancing for model selection.
result Meta-learner selects the best base learner based on actual realized regret.
Recently, it has been shown how sampling actions from the predictive distribution over the optimal action-sometimes called Thompson sampling-can be applied to solve sequential adaptive control problems, when the optimal policy is known for each possible environment. The predictive distribution can then be constructed b…
This research proposes a CL model for RNNs to handle sequential data without forgetting.
problem Learning in dynamic environments without forgetting previous knowledge for sequential data.
method A Recurrent Neural Network (RNN) model with Elastic Weight Consolidation (EWC) for CL.
result The proposed model outperforms EWC and RNNs on CL benchmarks for sequential data.
INTAGS uses interactive simulation to improve realism in multi-agent systems.
problem Challenges in developing realistic agent-based simulators for multi-agent systems.
method INTAGS introduces a novel metric to evaluate the difference between real and synthetic multi-agent systems, optimizing a stochastic policy in reinforcement learning to adapt to interactive sequential decision-making environments.
result INTAGS generates more realistic market data compared to state-of-the-art approaches.
Recursive experts improve dynamic sequential learning systems.
problem Adapt to changing environments in sequential learning.
method Design hyper-experts that recursively merge to achieve optimal performance.
result Achieve minimax optimal regret bounds up to constant factors.
Online convex optimization is a sequential prediction framework with the goal to track and adapt to the environment through evaluating proper convex loss functions. We study efficient particle filtering methods from the perspective of such a framework. We formulate an efficient particle filtering methods for the non-st…
Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environments - metalearning agents must explore again instead of immediately exploiting previously discover…
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.
FADE adapts machine learning models to evolving data efficiently.
problem Sequential covariate shift in dynamic environments.
method FADE uses Fisher information geometry for robust learning under SCS.
result FADE achieves up to 19% higher accuracy under severe shifts.
In a noisy environment, a lossy speech signal can be automatically restored by a listener if he/she knows the language well. That is, with the built-in knowledge of a "language model", a listener may effectively suppress noise interference and retrieve the target speech signals. Accordingly, we argue that familiarity w…
The paper tackles finding optimal treatment sequences in continuous state spaces.
problem Finding counterfactually optimal action sequences in continuous state spaces.
method Formalizes the problem using finite horizon Markov decision processes and structural causal models. Develops a search method based on the A* algorithm.
result The method can find optimal action sequences in polynomial time under certain conditions.
Model-based approaches bear great promise for decision making of agents interacting with the physical world. In the context of spatial environments, different types of problems such as localisation, mapping, navigation or autonomous exploration are typically adressed with specialised methods, often relying on detailed …
LF-IBIS learns optimal policies online without explicit likelihood.
problem Bayesian RL challenges due to intractable likelihood functions.
method Combines ABC with IBIS for online belief updates.
result Approximates posterior distributions for policies and parameters.
Improves RL planning by proposing sub-goals hierarchically.
problem Sequential planning assumption in RL.
method Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS).
result Improves navigation and control tasks.
Bayesian reflex models AI learning like the autonomic nervous system.
problem Online learning in dynamic AI environments.
method Bayesian online algorithms with belief maintenance, sequential updating, and uncertainty-driven action balancing.
result Unified framework for adaptive AI learning.
Competition aims to develop sample-efficient reinforcement learning methods.
problem Limited access to samples in reinforcement learning.
method Develops algorithms leveraging human demonstrations in Minecraft.
result Fosters innovation in sample-efficient reinforcement learning.
Paper compares semi-supervised training for differentiable particle filters.
problem Lack of labelled data in real-world applications.
method Compares two semi-supervised training objectives.
result Improved performance in environments with scarce labelled data.
The free energy functional has recently been proposed as a variational principle for bounded rational decision-making, since it instantiates a natural trade-off between utility gains and information processing costs that can be axiomatically derived. Here we apply the free energy principle to general decision trees tha…
Bayesian RL tackles uncertainty with deep generative models and sequential samplers.
problem Optimal decision-making in uncertain environments with limited data.
method Bayesian approach using deep generative models and prequential scoring rule for posterior inference. Policy learning via expected Thompson sampling.
result Improves policy learning in high-dimensional parameter spaces and continuous action spaces.
Safe actions learned in finite trials, without infinite exploration.
problem Learning safe actions in unknown environments efficiently.
method Defining a handicap metric and using sequential probability ratio test for discarding unsafe actions.
result Achieves constant handicap, discarding unsafe machines with probability one in finite rounds.
Paper introduces probabilistic digital twins for optimal decision making under uncertainty.
problem Optimal sequential decision making under incomplete and uncertain information.
method Formal definition of epistemic uncertainty using measure theory, and solution via deep reinforcement learning.
result Proposes a generic approximate solution for optimal sequential decision making.
Sparse Meta Networks adapt deep neural networks incrementally for fast learning.
problem Training deep neural networks is slow and impractical for complex, changing environments.
method Sparse Meta Networks use a memory layer to learn online sequential adaptation, accumulating fast-weights incrementally.
result Sparse Meta Networks achieve strong performance in various sequential adaptation scenarios.
Develops methods for finding counterfactual explanations in sequential decision making.
problem Finding counterfactual explanations for sequential decision making processes.
method Formal characterization of sequential actions and states using Markov decision processes and Gumbel-Max structural causal model. Introduces a polynomial time algorithm based on dynamic programming.
result Algorithm finds optimal counterfactual explanations for sequential decision making.
We consider the problem of how a teacher algorithm can enable an unknown Deep Reinforcement Learning (DRL) student to become good at a skill over a wide range of diverse environments. To do so, we study how a teacher algorithm can learn to generate a learning curriculum, whereby it sequentially samples parameters contr…
Reinforcement learning aims at searching the best policy model for decision making, and has been shown powerful for sequential recommendations. The training of the policy by reinforcement learning, however, is placed in an environment. In many real-world applications, however, the policy training in the real environmen…
Bayesian approach learns causal concepts from diverse social surveys.
problem Inferring causal concepts from heterogeneous data with sparse changes.
method Hierarchical Bayesian model with sequential Monte Carlo sampling.
result Model infers meaningful causal concepts and plausible relations.
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.
Unified framework for human-like decision making in various sequential tasks.
problem Real-life decision-making involves diverse strategies leading to similar outcomes.
method Two-stream reward processing mechanism for flexible and unified models.
result Framework unified MAB, CB, and RL with comparable performance.
New approach for adaptive conformal inference using Blackwell's theory.
problem Non-exchangeable environments in sequential conformal inference.
method Reinterpretation of ACI as a game, construction of coverage and efficiency objectives, approachability strategy.
result Algorithm achieves strong theoretical guarantees and practical insights.
New method optimizes decision-making in uncertain environments.
problem Optimal decision-making under partial observability.
method Nested sequential Monte Carlo algorithm for continuous POMDPs.
result Demonstrated effectiveness on continuous POMDP benchmarks.
The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward functions for environments with the same (or similar) dynamical models. We propose to l…
Develops methods to test nonstationarity and detect change points in RL.
problem Nonstationary environments in reinforcement learning.
method Consistent testing procedure and change point detection method.
result Validates the effectiveness of the proposed methods in real data.
Bayesian Federated Learning improves model reliability in dynamic environments.
problem Uncertainty quantification and robust adaptation in distributed learning.
method Proposes a continual BFL framework using SGLD for sequential updates and continual learning challenges.
result Continual Bayesian updates preserve knowledge and adapt to evolving data.
Paper proposes a hybrid model for financial time series prediction using sentiment analysis.
problem Challenges in forecasting in non-stationary, complex environments with heterogeneous data.
method Hybrid model combining GANs with NLP-based sentiment analysis.
result Hybrid model enhances robustness in non-stationary environments.
Applications in machine learning, optimization, and control require the sequential selection of a few system elements, such as sensors, data, or actuators, to optimize the system performance across multiple time steps. However, in failure-prone and adversarial environments, sensors get attacked, data get deleted, and a…
Sequential screening and dynamic regret in multi-armed bandits with arriving arms
problem Sequential experimentation with expanding arm set
method UCB-AA with preliminary screening
result Regret bounds depend on arrival process
We consider a stochastic linear bandit model in which the available actions correspond to arbitrary context vectors whose associated rewards follow a non-stationary linear regression model. In this setting, the unknown regression parameter is allowed to vary in time. To address this problem, we propose D-LinUCB, a nove…
Paper develops a framework for learning interpretable representations of sequential decision behavior.
problem Obtaining a transparent description of existing behavior.
method Inverse decision modeling framework, formalizing both forward and inverse problems.
result Learning interpretable representations of behavior, including suboptimal actions, biased beliefs, and imperfect knowledge.