Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

306089119 · Jun 202019922001200920172026
48 results for max reward

Study shows fast rates for inverse reinforcement learning with linear rewards.

problem Entropy-regularized min-max inverse reinforcement learning in finite-horizon MDPs.
method Structural and statistical analysis of Min-Max-IRL with pseudo-self-concordance.
result Both trajectory-level KL divergence and parameter error decay at O(n1)\mathcal{O}(n^{-1}).

We consider the Max KK-Armed Bandit problem, where a learning agent is faced with several sources (arms) of items (rewards), and interested in finding the best item overall. At each time step the agent chooses an arm, and obtains a random real valued reward. The rewards of each arm are assumed to be i.i.d., with an un…

2015-08-23abs ↗pdf ↗

We consider the Max KK-Armed Bandit problem, where a learning agent is faced with several stochastic arms, each a source of i.i.d. rewards of unknown distribution. At each time step the agent chooses an arm, and observes the reward of the obtained sample. Each sample is considered here as a separate item with the rewa…

2015-12-23abs ↗pdf ↗

The paper tackles a bandit problem with infinitely many arms per group, aiming to identify the group with the highest quantile reward.

problem Max-quantile group bandit problem with infinitely many arms per group.
method Two-step algorithm: first request arms from each group, then apply a finite-arm max-quantile bandit algorithm.
result Characterization of instance-dependent and worst-case regret, with matching lower bounds.

In this paper, we study the stochastic combinatorial multi-armed bandit (CMAB) framework that allows a general nonlinear reward function, whose expected value may not depend only on the means of the input random variables but possibly on the entire distributions of these variables. Our framework enables a much larger c…

2016-10-20abs ↗pdf ↗

New approach to multi-armed bandit problem aims to maximize highest total reward.

problem Traditional multi-armed bandit problem objective of maximizing total reward is not suitable in certain applications.
method Adaptive explore-then-commit policy with confidence bounds and adaptive stopping criterion.
result Achieves asymptotic and worst-case regret bounds for the new objective.

EBIL simplifies IL by estimating expert energy as reward, achieving effective performance.

problem Recovering optimal policy from expert demonstrations without reward signals.
method EBIL uses a two-stage solution: first estimating expert energy as reward, then learning policy.
result EBIL achieves effective performance and interpretable reward signals.

Efficient exploration is an unsolved problem in Reinforcement Learning which is usually addressed by reactively rewarding the agent for fortuitously encountering novel situations. This paper introduces an efficient active exploration algorithm, Model-Based Active eXploration (MAX), which uses an ensemble of forward mod…

2018-10-29abs ↗pdf ↗

Off-policy evaluation for MNAR rewards in MDPs

problem Off-policy evaluation in MDPs with MNAR rewards
method Formalizing a reward-dependent propensity model and using future states as shadow variables
result Proposed an Fitted-Q-Evaluation-style estimator that propagates recovered rewards while allowing target policies to depend on past missingness indicators

New method uses rank-conditioned Horvitz-Thompson estimation for unbiased sample reuse in Plackett-Luce best-of-K objective.

problem Estimating the expected maximum reward in Plackett-Luce draws without replacement.
method Rank-conditioned Horvitz-Thompson estimation with joint-score REINFORCE for unbiased sample reuse.
result Unbiased estimation of the Plackett-Luce best-of-K objective with finite second moment guarantees.

This paper studies the Best-of-K Bandit game: At each time the player chooses a subset S among all N-choose-K possible options and observes reward max(X(i) : i in S) where X is a random vector drawn from a joint distribution. The objective is to identify the subset that achieves the highest expected reward with high pr…

2016-03-09abs ↗pdf ↗

A new algorithm improves sample complexity for thresholding in Monte Carlo Tree Search.

problem Determining if the root node value of a tree is at least a given threshold.
method Developed a δ-correct sequential sampling algorithm based on the Track-and-Stop strategy.
result Ratio-based modification of D-Tracking strategy reduces sample complexity and computational cost.

The paper analyzes RLHF with human feedback and provides convergence results for MLE and pessimistic MLE.

problem Improving RLHF with human feedback from pairwise or KK-wise comparisons.
method Theoretical framework for RLHF with convergence analysis of MLE and pessimistic MLE.
result MLE fails but pessimistic MLE provides improved policies under certain coverage assumptions.

We consider stochastic multi-armed bandit problems with complex actions over a set of basic arms, where the decision maker plays a complex action rather than a basic arm in each round. The reward of the complex action is some function of the basic arms' rewards, and the feedback observed may not necessarily be the rewa…

2013-11-03abs ↗pdf ↗

In reinforcement learning the Q-values summarize the expected future rewards that the agent will attain. However, they cannot capture the epistemic uncertainty about those rewards. In this work we derive a new Bellman operator with associated fixed point we call the `knowledge values'. These K-values compress both the …

2018-07-25abs ↗pdf ↗

Optimal best arm identification for multi-objective bandits with fixed error probability.

problem Identifying the best arm for each of multiple objectives with fixed confidence.
method Surrogate proportions to sample arms at each time step, eliminating max-min optimisation.
result Asymptotically optimal algorithm for multi-objective best arm identification.

The paper tackles non-stationary MAB with periodic rewards.

problem Non-stationary mean rewards over time in a business context.
method Combines Fourier analysis with confidence-bound learning to estimate periods and minimize regret.
result Proposes a near-optimal policy with a regret bound of O(Tk=1KTk)O(\sqrt{T\sum_{k=1}^K T_k}).

New algorithm reduces unfairness in bandit problems by balancing exploration and exploitation.

problem Fairness in bandit problems where early participants can be unfairly disadvantaged.
method Introduces extsf{UCB-HARE} algorithm that balances exploration and exploitation using inverse-weighted harmonic rank schedule.
result Algorithm extsf{UCB-HARE} achieves regret matching the lower bound Ω(σkmax(1,q)/T)Ω(σ\sqrt{k^{\max(1,q)}/T}) for q>1q>1.

Improves RLHF sample efficiency by scaling reward complexity polynomially.

problem Exponential sample complexity in RLHF algorithms for skewed preferences.
method SE-POPO, an online RLHF algorithm that achieves polynomial sample complexity.
result SE-POPO outperforms existing algorithms in sample efficiency.

Unified approach to path planning using probabilistic inference on factor graphs.

problem Path planning problems using probabilistic inference.
method Unified framework using probabilistic factor graphs and message composition rules.
result Unified approach includes various algorithms like Sum-product, Max-product, Dynamic programming, and mixed criteria.

The paper identifies all ε-optimal arms in a bandit problem with Gaussian rewards.

problem Identifying all ε-optimal arms in a finite stochastic multi-armed bandit with Gaussian rewards.
method The paper provides two lower bounds and a Track-and-Stop strategy to solve the problem, with an efficient numerical method to solve the convex max-min program.
result The Track-and-Stop strategy has asymptotically optimal average sample complexity in the regime of low risk.

Equity-Transformer solves NP-hard min-max routing problems efficiently.

problem Min-max routing problems with multiple agents and large-scale applications.
method Sequential planning approach with Transformer and equitable workload distribution inductive biases.
result Significant runtime and cost reductions in min-max mTSP and min-max mPDP tasks.

Study max- and min-stability under first-order stochastic dominance, finding new functional characterizations.

problem Understanding max- and min-stability in stochastic dominance.
method Representation theorem for functionals satisfying max-stability, combining max- and min-stability to define Lambda-quantiles.
result New characterizations of functionals, including Lambda-quantiles, in finance and political science.

Max-min margin Markov networks improve consistency in structured prediction.

problem Statistical inconsistency in max-margin methods for structured prediction.
method Defining a max-min margin formulation to overcome statistical inconsistency.
result Proves consistency and provides an explicit algorithm with finite sample generalization bounds.

Estimates parameters in max-linear Bayesian networks with noise.

problem Causal inference in extreme-value settings with noise parameters.
method Max-plus algebra and logarithm transformation, normal distribution estimation, EM algorithm and quadratic optimization.
result An estimator of a parameter for each edge in a DAG is normally distributed.

New algorithms reduce sample complexity for multiclass contextual bandits.

problem Designing efficient algorithms for multiclass contextual bandits with sparse rewards.
method Two complementary approaches: decision-estimation coefficient analysis and low-variance exploration.
result Achieved optimal sample complexity bounds for multiclass contextual bandits.

The paper solves min-max widths on a 3-sphere and strengthens multiplicity theorems.

problem Which min-max widths of the unit 3-sphere lie between 2π22π^2 and 8π?
method Homological min-max theory and stronger versions of multiplicity one theorems.
result Proves the 10th to 13th min-max widths of the unit 3-sphere lie between 2π22π^2 and 8π.

In this paper, we propose a cost-aware cascading bandits model, a new variant of multi-armed ban- dits with cascading feedback, by considering the random cost of pulling arms. In each step, the learning agent chooses an ordered list of items and examines them sequentially, until certain stopping condition is satisfied.…

2018-05-22abs ↗pdf ↗

Adaptive momentum method solves non-convex min-max problems.

problem Non-convex min-max optimization problems in training generative adversarial networks.
method Proposes an adaptive momentum algorithm for non-convex min-max optimization.
result Establishes non-asymptotic convergence rates for the proposed algorithm.