New algorithm for nonstationary multi-armed bandits with optimal performance.
problem Nonstationary multi-armed bandits with changing model parameters over time.
method Adaptive Resetting Bandit (ADR-bandit) algorithm using adaptive windowing techniques.
result ADR-bandit achieves nearly optimal performance in both abrupt and gradual changes.
Reinforcement learning (RL) methods learn optimal decisions in the presence of a stationary environment. However, the stationary assumption on the environment is very restrictive. In many real world problems like traffic signal control, robotic applications, one often encounters situations with non-stationary environme…
Self-supervised policy adapts after deployment without rewards.
problem Generalizing reinforcement learning policies across different environments.
method Uses self-supervision to train policies in new environments without reward signals.
result Significant improvements in generalization across diverse environments.
New method recovers causal DAGs from general environments without strict assumptions.
problem Recovering causal DAGs from real-world data with varying distributions.
method Formalizes desiderata for causal representation learning in general environments, leveraging sufficient change conditions up to third-order derivatives.
result Fully recovers latent DAG and identifies latent variables up to minor indeterminacies under nonparametric mixing.
Framework for robust decision making in changing environments with privacy constraints.
problem Interactive decision making in changing environments with constraints.
method Hybrid Decision Making with Structured Observations (hybrid DMSO) framework, local differentially private decision making, query-based learning, robust and smooth decision making.
result Strong connections and bounds derived for DEC, SQ dimension, local minimax complexity, learnability, and joint differential privacy.
New bandit algorithm detects and adapts to seasonal changes in rewards.
problem Adapting to abrupt changes in user preferences during events.
method Detects and adapts to seasonal changes in reward function.
result Outperforms state-of-the-art algorithms for non-stationary environments.
Adaptive policies for multi-agent RL improve adaptiveness in changing environments.
problem Non-stationarity in multi-agent reinforcement learning where other agents may alter their policies.
method Train multiple adaptive policies for each agent and a policy predictor to select the best policy at execution time.
result Agents trained with our method outperform state-of-the-art methods in all tested environments.
OSAMD adapts online to changing distributions with limited labels.
problem Models struggle with continual distribution shifts and expensive labeling in changing environments.
method Online Active Continual Adaptation with OSAMD, an online teacher-student structure and margin-based criterion.
result OSAMD achieves favorable dynamic regret bounds under changing environments with limited labels.
A new buffer system improves continual learning in RL agents by adapting to changing environments.
problem Improving RL agents' ability to learn from changing environments over time.
method Multi-timescale replay buffer combined with invariant risk minimization.
result The method shows improvement over baselines in continual learning settings.
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.
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.
Autonomous lane changing is a critical feature for advanced autonomous driving systems, that involves several challenges such as uncertainty in other driver's behaviors and the trade-off between safety and agility. In this work, we develop a novel simulation environment that emulates these challenges and train a deep r…
AdaRL adapts quickly to new environments with minimal data.
problem Quickly adapting to new environments in reinforcement learning.
method AdaRL uses a parsimonious graphical representation to encode changes across domains.
result AdaRL can efficiently adapt policies to target domains with few samples.
Paper proposes a method for learning and planning in time-varying environments.
problem Learning and planning in unknown, time-varying environments.
method Computes the maximally likely model of the environment using maximum likelihood estimation.
result Generalizes learning algorithms for time-invariant Markov decision processes to time-varying ones.
High-dimensional always-changing environments constitute a hard challenge for current reinforcement learning techniques. Artificial agents, nowadays, are often trained off-line in very static and controlled conditions in simulation such that training observations can be thought as sampled i.i.d. from the entire observa…
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.
Proposes a method to adapt models in nonstationary environments using ℓ1 regularization.
problem Adapting models to nonstationary environments in machine learning.
method Integrates ℓ1 regularization of differences between source and target parameters.
result Effective balance of stability and plasticity in model adaptation.
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…
Novel graph-spanning algorithm detects changes in high-dimensional data.
problem Detecting changes in high-dimensional data across various distributions.
method Graph-spanning algorithm designed for offline and online data.
result Achieves high detection power with minimal separation rate.
New method detects anomalies in systems influenced by their environment.
problem Detecting anomalies in systems under environmental influence.
method Adversarial learning and time series representation learning.
result Successfully addresses label sparsity and subjectivity in anomaly detection.
New algorithms detect changes in non-stationary MABs for better performance.
problem Non-stationary MAB environments where arm reward distributions change over time.
method Modular Detection Augmented Bandit (DAB) procedures with improved performance lower bounds.
result Modular DAB procedures achieve order-optimal regret bounds for various change detectors and bandit algorithms.
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.
BAM integrates new data while selectively remembering past observations.
problem Slow adaptation and convergence to incorrect parameter values in non-stationary environments.
method Bayes' theorem with adaptive memory selection.
result BAM generalizes and demonstrates continuous adaptation in changing environments.
A new method shapes reinforcement learning environments by abstracting large state spaces.
problem Learning in large, noisy environments with sparse feedback.
method Environment shaping using state abstraction.
result Agent's policy in shaped environment preserves near-optimal behavior in original environment.
Multi-armed bandit algorithms have become a reference solution for handling the explore/exploit dilemma in recommender systems, and many other important real-world problems, such as display advertisement. However, such algorithms usually assume a stationary reward distribution, which hardly holds in practice as users' …
Robust OPE framework uses human inputs to improve policy evaluation in changing environments.
problem Inaccurate policy evaluations due to shifts in environment properties.
method Adapts OPE methods to shifts on user-inputted covariates, providing more realistic utility estimates.
result Robust OPE framework yields less pessimistic policy evaluations and captures realistic dataset shifts.
Tree-based regularization improves latent variable inference from related datasets.
problem Inferring latent variables from multiple related datasets in causal systems.
method Tree-Based Regularization (TBR) for sparse changes across environments.
result TBR identifies true latent variables up to simple transformations under sparse changes.
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.
New algorithms detect and react to multiple change points in online learning.
problem Learning under multiple change points in environments with unknown and frequent shifts.
method Proposed Anytime Tracking CUSUM (ATC) algorithms that balance detection of significant shifts.
result Properly tuned ATC algorithms achieve nearly minimax-optimal performance.
Learning in a non-stationary environment is an inevitable problem when applying machine learning algorithm to real world environment. Learning new tasks without forgetting the previous knowledge is a challenge issue in machine learning. We propose a Kalman Filter based modifier to maintain the performance of Neural Net…
The paper proposes a method to adapt machine learning models to changing conditions.
problem Machine learning models need to adapt to new conditions in a constantly changing environment.
method Reuse knowledge from existing models to train future generations.
result The proposed method allows machine learning models to adapt and survive in a dynamic environment.
We propose algorithms for online principal component analysis (PCA) and variance minimization for adaptive settings. Previous literature has focused on upper bounding the static adversarial regret, whose comparator is the optimal fixed action in hindsight. However, static regret is not an appropriate metric when the un…
AACC improves RL performance in changing environments.
problem Deterioration of RL performance in real-world tasks.
method Formalizes CMDPs, proposes AACC for contextual RL.
result AACC outperforms baselines in various simulated environments.
We study the non-stationary stochastic multiarmed bandit (MAB) problem and propose two generic algorithms, namely, the limited memory deterministic sequencing of exploration and exploitation (LM-DSEE) and the Sliding-Window Upper Confidence Bound# (SW-UCB#). We rigorously analyze these algorithms in abruptly-changing a…
The paper tackles policy learning in dynamic environments using causal methods.
problem Existing reinforcement learning algorithms assume static mechanisms, but real-world systems often have changing mechanisms.
method The paper introduces multi-environment contextual bandits and policy invariance to handle environmental shifts.
result An optimal invariant policy is guaranteed to generalize across environments under suitable assumptions.
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that…
Concept drift is formally defined as the change in joint distribution of a set of input variables X and a target variable y. The two types of drift that are extensively studied are real drift and virtual drift where the former is the change in posterior probabilities p(y|X) while the latter is the change in distributio…
Optimizes latency and false alarm probability in change detection problems.
problem Balancing latency and false alarms in non-stationary environments.
method Develops order-optimal change detectors under specified latency and false alarm levels.
result Derives a universal lower bound on latency and develops order-optimal detectors.
Study adapts combinatorial semi-bandit for piecewise stationary, causally related rewards.
problem Nonstationary environment with changing base arms' distributions and causal relationships.
method Upper Confidence Bound (UCB) algorithm with change-point detector and group restart strategy.
result Regret upper bound reflecting effects of structural and distribution changes.
New algorithm tackles non-stationary delayed feedback in recommender systems.
problem Challenges in learning from delayed feedback in non-stationary environments.
method Developed a UCRL-based algorithm for non-stationary, delayed bandits with intermediate observations.
result Sublinear regret guarantees for the proposed algorithm in non-stationary delayed environments.
To deal with changing environments, a new performance measure -- adaptive regret, defined as the maximum static regret over any interval, was proposed in online learning. Under the setting of online convex optimization, several algorithms have been successfully developed to minimize the adaptive regret. However, existi…
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that…
This work introduces a method to attribute model performance drops to distribution shifts.
problem Attributing performance drops of machine learning models to distribution shifts.
method Formulated as a cooperative game, value of a set of distributions is defined as the change in model performance when only that set of distributions changes. Importance weighting method for computing the value of an arbitrary set of distributions is derived. Quantifying the contribution of each distribution as its Shapley value.
result Demonstrated the effectiveness of the method on various case studies.
Develops RL algorithm for lifelong non-stationary environments.
problem Challenges of reinforcement learning in environments with persistent change.
method Formalizes lifelong non-stationarity, uses latent variable models, and leverages online learning and probabilistic inference.
result Substantial improvement in performance over non-reasoning approaches in lifelong non-stationary environments.
A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments. Recent studies have proposed "meta" algorithms that convert any online learning algorithm to one that is adaptive to changing environments, where the adaptivity is analyzed in a quantity called the strongly-ad…
Lane change is a challenging task which requires delicate actions to ensure safety and comfort. Some recent studies have attempted to solve the lane-change control problem with Reinforcement Learning (RL), yet the action is confined to discrete action space. To overcome this limitation, we formulate the lane change beh…
Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself a…
Optimization in the presence of sharp (non-Lipschitz), unpredictable (w.r.t. time and amount) changes is a challenging and largely unexplored problem of great significance. We consider the class of piecewise Lipschitz functions, which is the most general online setting considered in the literature for the problem, and …