Bayesian method estimates dynamics from near-optimal trajectories.
problem Estimating dynamics from near-optimal expert trajectories in reinforcement learning.
method Constraint-based Bayesian approach integrating expert near-optimality.
result Significant improvements in decision-making and transfer success.
New algorithm clusters trajectories from multiple Markov chains with near-optimal error.
problem Clustering trajectories from multiple unknown Markov chains.
method Two-stage algorithm: spectral clustering followed by likelihood-based refinement.
result Achieves near-optimal clustering error with high probability.
Estimates missing mass in Markovian sequences with linear runtime and near-optimal risk.
problem Estimating missing mass in Markovian sequences.
method Windowed Good-Turing (WingIt) estimator.
result Risk decays as O ~ ( T m i x / n ) \widetilde{O}(\mathsf{T_{mix}}/n) O ( T mix / n ) , independent of state space size. Standard reinforcement learning methods aim to master one way of solving a task whereas there may exist multiple near-optimal policies. Being able to identify this collection of near-optimal policies can allow a domain expert to efficiently explore the space of reasonable solutions. Unfortunately, existing approaches t…
Many prediction domains, such as ad placement, recommendation, trajectory prediction, and document summarization, require predicting a set or list of options. Such lists are often evaluated using submodular reward functions that measure both quality and diversity. We propose a simple, efficient, and provably near-optim…
New algorithm infers reward function from agent's learning trajectories.
problem Inferring reward function from agent's learning data.
method Gradient-based approach to recover reward function.
result Improved performance compared to state-of-the-art methods.
A new method learns policies from sub-optimal trajectories.
problem Reinforcement learning's brittleness and difficulty in tuning.
method Conditioning policies on the reward of sub-optimal trajectories.
result Effective policies can be learned without expert demonstrations.
Recent years have seen a flurry of activities in designing provably efficient nonconvex procedures for solving statistical estimation problems. Due to the highly nonconvex nature of the empirical loss, state-of-the-art procedures often require proper regularization (e.g. trimming, regularized cost, projection) in order…
Transformers learn to make decisions in new contexts from offline data.
problem Understanding when and how transformers can perform in-context reinforcement learning.
method Theoretical framework analyzing supervised pretraining for ICRL, including algorithm distillation and decision-pretrained transformers.
result Transformers can efficiently approximate optimal reinforcement learning algorithms for various environments.
Study infers interaction kernels from multiple particle trajectories.
problem Inferring interaction kernels from multiple particle trajectories in stochastic systems.
method Nonparametric inference approach based on regularized maximum likelihood estimator.
result Consistent estimator with near-optimal learning rate independent of state space dimension.
Algorithm learns linear systems from partial observations with near-optimal rate.
problem Identifying linear dynamical systems from partial observations, especially those with long-term memory.
method Multi-scale low-rank approximation using SVD on Hankel matrices of increasing sizes, combined with Fourier domain concentration bounds.
result Near-optimal rate of $\widetilde O\left(\sqrt\frac{d}{T}
ight)$ in H 2 \mathcal{H}_2 H 2 error, with logarithmic dependence on memory length. New algorithm reduces sample complexity for planning in MDPs.
problem Planning in MDPs with unknown transitions.
method MDP-GapE, a trajectory-based MCTS algorithm.
result Proves upper bound on sample complexity in terms of sub-optimality gaps.
Adaptive OMD reduces variance in learning optimal strategies for imperfect information games.
problem High variance in learning optimal strategies for imperfect information games.
method Fixed sampling approach with locally applied Online Mirror Descent (OMD) algorithm.
result Convergence rate of i l d e O ( T − 1 / 2 ) ilde{\mathcal{O}}(T^{-1/2}) i l d e O ( T − 1/2 ) with high probability. A new framework isolates exploration challenges in RL without explicit rewards.
problem Challenges in reinforcement learning, especially exploration.
method Reward-free RL framework, collecting trajectories without a reward function, then computing policies for various reward functions.
result Efficient algorithm that conducts exploration and computes near-optimal policies for multiple reward functions.
Task-agnostic RL tackles exploration in MDPs with multiple tasks.
problem Challenges in reinforcement learning with multiple tasks or conflicting objectives.
method Task-agnostic RL framework, UCBZero algorithm.
result UCBZero finds near-optimal policies for multiple tasks efficiently.
Q Q Q -learning with function approximation is one of the most popular methods in reinforcement learning. Though the idea of using function approximation was proposed at least 60 years ago, even in the simplest setup, i.e, approximating Q Q Q -functions with linear functions, it is still an open problem on how to design a pr…
New methods tackle robust reinforcement learning in sparse, corrupted data.
problem Tackles robust reinforcement learning in sparse, corrupted data.
method Proposes actor-critic methods with sparse robust estimator oracles.
result First non-vacuous guarantees in high-dimensional sparse MDPs with single-policy concentrability coverage.
We study discrete time dynamical systems governed by the state equation h t + 1 = φ ( A h t + B u t ) h_{t+1}=φ(Ah_t+Bu_t) h t + 1 = φ ( A h t + B u t ) . Here A , B A,B A , B are weight matrices, φ φ φ is an activation function, and u t u_t u t is the input data. This relation is the backbone of recurrent neural networks (e.g. LSTMs) which have broad applications in sequential learning tasks. …
Paper tackles non-stationary kernelized bandits with near-optimal algorithm.
problem Minimizing regret in a time-varying reward function.
method Near-optimal algorithm with a novel restarting phased elimination with random permutation (R-PERP).
result Regret upper bound matches the lower bound, making the algorithm near-optimal.
Large learning rates improve neural network generalization, study shows.
problem Understanding why large learning rates lead to better neural network generalization.
method Visual analysis of training and testing loss landscapes, introduction of a nonlinear model.
result Extended phase with large learning rates leads to near-optimal generalization.
A critical flaw of existing inverse reinforcement learning (IRL) methods is their inability to significantly outperform the demonstrator. This is because IRL typically seeks a reward function that makes the demonstrator appear near-optimal, rather than inferring the underlying intentions of the demonstrator that may ha…
Paper tackles RLHF with DCPPO method, proving near-optimal suboptimality.
problem Challenges in offline RLHF with limited human feedback and bounded rationality.
method DCPPO method involving three stages: MLE, reward function recovery, and pessimistic value iteration.
result DCPPO's suboptimality almost matches classical pessimistic offline RL in terms of distribution shift and dimension.
We study the worst-case adaptive optimization problem with budget constraint that is useful for modeling various practical applications in artificial intelligence and machine learning. We investigate the near-optimality of greedy algorithms for this problem with both modular and non-modular cost functions. In both case…
Efficient streaming algorithms for robust statistics with near-optimal memory.
problem High-dimensional robust statistics tasks in streaming model.
method First efficient streaming algorithms with near-optimal memory requirements.
result Near-optimal error guarantees and space complexity nearly-linear in the dimension for robust mean estimation.
The paper offers simple, near-optimal algorithms for multi-group learning.
problem Learning predictors within subgroups of a population, addressing fairness and hidden stratification.
method Studies the structure of solutions and provides simple, near-optimal algorithms.
result Simple and near-optimal algorithms for multi-group learning.
GP-MRO discovers robust mixed strategies for unknown objectives.
problem Optimizing unknown objectives against worst-case uncertain parameters.
method Sequential learning from noisy point evaluations, combining online learning and Gaussian processes.
result GP-MRO finds robust mixed strategies that significantly improve performance over deterministic strategies.
New algorithm reduces RL complexity with low switching costs.
problem Exploration-exploitation dilemma in RL with complex models.
method Monotonic Q-Learning with Upper Confidence Bound (MQL-UCB) for RL with general function approximation.
result Achieves minimax optimal regret of O ( d H K ) O(d\sqrt{HK}) O ( d H K ) and near-optimal policy switching cost. We study the problem of regret minimization for distributed bandits learning, in which M M M agents work collaboratively to minimize their total regret under the coordination of a central server. Our goal is to design communication protocols with near-optimal regret and little communication cost, which is measured by the…
Paper tackles clustering with ordinal comparisons, achieving near-optimal results.
problem Clustering with ordinal comparisons when similarity measures are not available.
method Two-step procedure: estimate similarity matrix from comparisons, then apply SDP clustering.
result Near-optimal recovery of planted clustering using near-optimal number of comparisons.
Federated Q-learning achieves linear speedup with heterogeneity, improving sample complexity.
problem Collaborative learning in distributed RL settings with limited data sharing.
method Analyzes synchronous and asynchronous federated Q-learning, proposes importance averaging.
result Achieves linear speedup with heterogeneity, robust to local trajectory heterogeneity.
New algorithm detects changes quickly without knowing parameters, near optimally.
problem Quickest change detection with unknown parameters.
method Leverages theoretical asymptotic properties to derive a scalable approximate algorithm with near optimal performance.
result Detects changes in constant complexity with near optimal performance.
Efficiently find near-optimal medical treatments with less trial and error.
problem Finding effective medical treatments through trial and error.
method Formalizes the problem, uses a causal inference framework, and proposes model-based dynamic programming and greedy algorithms.
result Our methods compare favorably to model-free reinforcement learning, offering a more transparent trade-off between search time and treatment efficacy.
New DP algorithms achieve near-optimal regret bounds for online learning problems.
problem Online learning problems with zero-loss solutions and differential privacy constraints.
method Developed new Differentially Private algorithms with near-optimal regret bounds.
result Achieved near-optimal regret bounds for various online prediction and convex optimization problems.
Algorithm extsc{Pedel} learns near-optimal policies efficiently on specific problems.
problem Learning near-optimal policies in linear MDPs with minimal samples.
method Online experiment design to focus exploration on relevant directions.
result Achieves instance-dependent complexity, outperforming minimax-optimal algorithms.
Improved algorithm for adaptive dueling bandits with near-optimal regret bound.
problem Non-stationary dueling bandits with unknown number of preference changes.
method Elimination-based rescheduling algorithm for adaptive dynamic regret.
result Near-optimal i l d e O ( S e x t t t C W T ) ilde{O}(\sqrt{S^{ exttt{CW}} T}) i l d e O ( S e x ttt C W T ) dynamic regret bound. We study the problem of discriminative sub-trajectory mining. Given two groups of trajectories, the goal of this problem is to extract moving patterns in the form of sub-trajectories which are more similar to sub-trajectories of one group and less similar to those of the other. We propose a new method called Statistica…
A single policy suffices for near-optimal parallel exploration in RL.
problem Quantitative effects of parallel exploration in reward-free RL.
method Using a single policy to guide exploration across all agents.
result Near-linear speedup and near-minimax optimality for linear MDPs.
Short proof for ideal polygons with near optimal orthogeodesic decomposition.
problem Decomposing ideal polygons into orthogeodesics.
method Short proof with orthogeodesic decomposition of length at most 2 log ( n ) 2 \log(n) 2 log ( n ) . result Optimal orthogeodesic decomposition of ideal polygons with length 2 log ( n ) 2 \log(n) 2 log ( n ) . A new UCB algorithm for heavy-tailed bandits with near-optimal regret.
problem Sequential decision making in uncertain environments with heavy-tailed rewards.
method Data-driven, distribution-free UCB algorithm combining resampled median-of-means and UCB.
result Near-optimal regret bound for heavy-tailed distributions.
New algorithm reduces bias in trained models, near-optimal performance proven.
problem Reduction of bias in trained machine learning models.
method Scalable post-processing algorithm for debiasing trained models, including deep neural networks (DNNs).
result Proven to be near-optimal by bounding its excess Bayes risk.
A new method finds diverse near-optimal portfolios using quality-diversity.
problem Optimizing financial portfolios with robustness to input parameter uncertainties.
method Quality-Diversity (QD) optimization using CVT-MAP-Elites algorithm.
result Diverse set of near-optimal portfolios identified.
Paper uses deep imitation learning to predict aircraft trajectories accurately.
problem Inefficient and costly Air Traffic Management system limits predictability.
method Generative Adversarial Imitation Learning framework with trajectory clustering and classification.
result Accurate predictions for entire trajectory stages, pre- and tactical.
Near-optimal algorithms for predicting across multiple loss functions efficiently.
problem Predicting optimally across various loss functions simultaneously.
method Developed near-optimal online and offline learning algorithms for omniprediction.
result Achieved near-optimal complexity for both online and offline settings.
New algorithms minimize risk in MNL bandits, achieving near-optimal performance.
problem Minimizing risk in multi-armed bandit problems.
method Designing algorithms for various risk criteria (e.g., CVaR, Sharpe ratio, entropy risk).
result Near-optimal regret for the designed algorithms.
Ensembles of random-feature models can't outperform a single large model.
problem Finding the optimal balance between model size and ensemble size.
method Deterministic equivalent risk estimates and scaling laws analysis.
result Ensembles of random-feature models achieve near-optimal performance only under specific conditions.
Paper infers human mobility from sparse trajectories.
problem Modeling and inferring human mobility from sparse trajectory data.
method Proposes a single trajectory inference algorithm and a deep learning architecture for multiple trajectories.
result Deep learning model achieves 2x overall accuracy improvement on sparse trajectories.
AE-LSVI identifies near-optimal policies in complex systems with minimal data.
problem Identifying near-optimal policies in complex, costly data acquisition systems.
method Combines optimism and pessimism for active exploration in a generative model setting.
result Proves near-optimal policy identification over entire state spaces with polynomial sample complexity.
Pattern ensembling fills in missing or inaccurate trajectory data.
problem Incompleteness, missing information, and inaccuracies in geolocation data.
method Probabilistically ensemble similar trajectory patterns from the vicinity.
result Reconstructs missing or unreliable trajectory segments effectively.