Related papers: Minimax Optimal Online Imitation Learning via Repl…
Many deployed learning systems must update models on streaming data under memory constraints. The default strategy, sequential fine-tuning on each new phase, is architecture-agnostic but often suffers catastrophic forgetting when later…
Imitation Learning is a sequential task where the learner tries to mimic an expert's action in order to achieve the best performance. Several algorithms have been proposed recently for this task. In this project, we aim at proposing a wide…
User behavior on online platforms is evolving, reflecting real-world changes in how people post, whether it's helpful messages or hate speech. Models that learn to capture this content can experience a decrease in performance over time due…
We introduce a model of online algorithms subject to strict constraints on data retention. An online learning algorithm encounters a stream of data points, one per round, generated by some stationary process. Crucially, each data point can…
Imitation learning is a central problem in reinforcement learning where the goal is to learn a policy that mimics the expert's behavior. In practice, it is often challenging to learn the expert policy from a limited number of demonstrations…
In this work, we study algorithms for learning in infinite-horizon undiscounted Markov decision processes (MDPs) with function approximation. We first show that the regret analysis of the Politex algorithm (a version of regularized policy…
Targeted for real world scenarios, online continual learning aims to learn new tasks from sequentially available data under the condition that each data is observed only once by the learner. Though recent works have made remarkable…
We study online adversarial imitation learning (AIL), where an agent learns from offline expert demonstrations and interacts with the environment online without access to rewards. Despite strong empirical results, the benefits of online…
We study online estimation in latent-variable models by recasting the problem as tracking a moving empirical equilibrium. Standard online EM and stochastic approximation analyses primarily study convergence toward the population parameter…
As machine learning systems increasingly train on self-annotated data, they risk reinforcing errors and becoming echo chambers of their own beliefs. We model this phenomenon by introducing a learning-theoretic framework: Online Learning in…
Imitation learning traditionally requires complete state-action demonstrations from optimal or near-optimal experts. These requirements severely limit practical applicability, as many real-world scenarios provide only state observations…
Inverse reinforcement learning (IRL), which infers reward functions from demonstrations, is a valuable tool for modeling and understanding decision-making behavior. Many variants of IRL have been developed to capture complexities of human…
Online-learning literature has focused on designing algorithms that ensure sub-linear growth of the cumulative long-term constraint violations. The drawback of this guarantee is that strictly feasible actions may cancel out constraint…
Uncertainty quantification is crucial in safety-critical systems, where decisions must be made under uncertainty. In particular, we consider the problem of online uncertainty quantification, where data points arrive sequentially. Online…
Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standard strategies face a core tradeoff: regularization-based methods (e.g., EWC) can overconstrain updates when task optima are weakly overlapping,…
Conventional hyperparameter optimization methods are computationally intensive and hard to generalize to scenarios that require dynamically adapting hyperparameters, such as life-long learning. Here, we propose an online hyperparameter…
We investigate the concept of algorithmic replicability introduced by Impagliazzo et al. 2022, Ghazi et al. 2021, Ahn et al. 2024 in an online setting. In our model, the input sequence received by the online learner is generated from…
We study the problem of offline Imitation Learning (IL) where an agent aims to learn an optimal expert behavior policy without additional online environment interactions. Instead, the agent is provided with a supplementary offline dataset…
The objective of offline RL is to learn optimal policies when a fixed exploratory demonstrations data-set is available and sampling additional observations is impossible (typically if this operation is either costly or rises ethical…
Online learning with expert advice is a fundamental problem of sequential prediction. In this problem, the algorithm has access to a set of $n$ "experts" who make predictions on each day. The goal on each day is to process these…