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

24487195 · Jun 202019922001200920172026
48 results for optimistic rewards

Kernel-based function approximation improves reinforcement learning performance.

problem Average reward reinforcement learning in infinite horizon settings.
method Optimistic algorithm based on kernel ridge regression.
result No-regret performance guarantees and confidence intervals for kernel-based predictions.

New algorithm reduces reinforcement learning regret to sqrt(T) without strong dynamics assumptions.

problem Infinite-horizon average-reward reinforcement learning with linear MDPs.
method Approximate by discounted-reward MDPs and apply optimistic value iteration.
result Achieves O(sqrt(T)) regret with polynomial complexity.

New findings on universal learning in contextual bandits with adversarial rewards.

problem Learning in contextual bandits with time-varying, adversarial rewards.
method Characterization of learnable processes and necessary/sufficient conditions for universal learning.
result Optimistic universal learning for contextual bandits with adversarial rewards is impossible in general.

New algorithm reduces regret for logistic bandits without κκ dependency.

problem Logistic bandits have poor frequentist regret guarantees due to large κκ.
method Optimistic algorithm based on self-normalized martingale tail-inequality.
result Achieves ildeO(T) ilde{\mathcal{O}}(\sqrt{T}) regret with no κκ dependency.

Paper tackles constrained bandit problems with a new learning framework.

problem Optimizing a black-box reward function subject to a black-box constraint function over a continuous space.
method Rectified Pessimistic-Optimistic Learning (RPOL) framework, incorporating optimistic and pessimistic GP bandit learning.
result RPOL achieves sublinear regret and minimal cumulative constraint violation.

Proposes Optimistic Pessimistically Initialised Q-Learning (OPIQ) for better exploration in RL.

problem Pessimistic initialisation of Q-values in deep RL leads to poor exploration performance.
method Augments pessimistically initialised Q-values with count-based bonuses to ensure optimism.
result OPIQ outperforms non-optimistic DQN variants in hard exploration tasks.

This paper analyzes how randomizing rewards in MBRL can improve performance without being overly optimistic.

problem The gap between theoretical worst-case regret analysis and empirical performance in MBRL.
method Reward randomization in model-based reinforcement learning (MBRL) with kernelized linear regulator (KNR) model.
result Reward randomization guarantees partial optimism and near-optimal worst-case regret.

New algorithm for average reward learning with bounded hitting time assumption.

problem Minimizing regret in average reward reinforcement learning with bounded hitting time.
method Optimistic Q-learning with a novel L\overline{L} operator for bounded hitting time.
result Regret bound of ildeO(H5SAT) ilde{O}(H^5 S\sqrt{AT}) for average reward learning.

Optimistic Thompson Sampling reduces regret in unknown multi-player games.

problem Navigating uncertainty in unknown multi-player games with strategic decision-making.
method Introduces Thompson Sampling algorithms that exploit opponents' actions and reward structures.
result Achieves over tenfold improvements in experimental budgets with logarithmic regret bound.

New RL algorithm tackles nonstationary MDPs with linear approximations and varying rewards.

problem Nonstationary reinforcement learning with evolving reward and state transition functions.
method Developed a new algorithm LSVI-UCB-Restart with periodic restart, and parameter-free Ada-LSVI-UCB-Restart for unknown variation budgets.
result First minimax dynamic regret lower bound for nonstationary linear MDPs and linear MDPs lower bound.

Study designs steering rewards for MFGs with unknown dynamics and model uncertainty.

problem Designing incentives for large populations of agents in MFGs with uncertain model details.
method Developed optimistic exploration algorithms for agents with no-adaptive regret behaviors.
result Sub-linear regret guarantees for cumulative gaps between agent behaviors and desired outcomes.

New algorithms reduce contextual bandits' regret without knowing reward noise variances.

problem Reducing regret in contextual bandits with unknown reward noise variances.
method Developed new algorithms based on the optimism principle.
result Regret scales as the square root of the sum of measurement variances, not the time horizon.

PROPO tackles non-stationary MDPs with efficient policy optimization.

problem Non-stationary MDPs with varying reward and transition kernels.
method PROPO, a periodic restarted optimistic policy optimization algorithm with sliding-window-based policy evaluation and improvement.
result PROPO achieves near-optimal performance in non-stationary MDPs.

An algorithm for maximizing rewards under linear cost constraints.

problem Maximizing rewards while adhering to cost constraints in a linear bandit problem.
method Proposes an upper-confidence bound algorithm called optimistic pessimistic linear bandit (OPLB) for constrained contextual linear bandits.
result Proves an O~(dTτc0)\widetilde{\mathcal{O}}(\frac{d\sqrt{T}}{τ-c_0}) bound on regret for the proposed algorithm.

New algorithm achieves nearly optimal regret with one-pass updates for GLB problems.

problem Generalized linear bandits with non-linear reward distributions.
method Jointly efficient algorithm using OMD estimator with one-pass updates.
result Nearly optimal regret bound with O(1)\mathcal{O}(1) time and space complexities per round.

New rule reduces exploration regret to logarithmic, improving bad episode handling.

problem Improving exploration regret in average reward MDPs.
method Replacing Doubling Trick with Vanishing Multiplicative rule in EVI-based algorithms.
result Regret is logarithmic under the new rule, significantly better than linear.

Optimistic Mirror Descent framework improves bidding strategies in non-stationary first-price auctions.

problem Optimizing bidding strategies in non-stationary first-price auctions.
method Introducing Optimistic Mirror Descent (OMD) framework with novel optimism configuration.
result Minimax-optimal dynamic regret rates achieved for non-stationary first-price auctions.

New RL method explores environments without rewards, achieving efficient policy generation.

problem Efficiently exploring unknown environments without predefined rewards.
method Optimistic value-iteration algorithm with kernel and neural function approximations.
result Achieves O~(1/ε2)\widetilde{\mathcal{O}}(1 /\varepsilon^2) sample complexity for generating policies or equilibria.

Optimistic algorithm reduces regret in non-stationary linear MDPs.

problem Efficient learning in non-stationary linear MDPs with evolving reward and transition.
method OPT-WLSVI, an optimistic model-free algorithm using exponential weights.
result Achieves a regret bound of O~(d5/4H2Δ1/4K3/4)\widetilde{\mathcal{O}}(d^{5/4}H^2 Δ^{1/4} K^{3/4}).

Improved POMDP regret to sqrt(T) with known observation model.

problem Average-reward POMDPs with unknown transition model but known observation model.
method Optimistic algorithm using deterministic policies and novel estimation techniques.
result First approach with regret guarantee of sqrt(T) against optimal policy.

New algorithms ensure policies perform at least as good as a baseline in reinforcement learning.

problem Learning policies that are guaranteed to perform at least as well as a baseline in reinforcement learning.
method Introduce conservative exploration for average reward and finite horizon problems, presenting two optimistic algorithms.
result Guaranteed performance of policies at least as good as a baseline, without hindering learning ability.

Algorithm learns optimal coordination for strategic agents in uncertain settings.

problem Optimizing rewards for strategic agents with private types and actions.
method Combines delaying mechanism, reward angle estimation, and LinUCB algorithm.
result Near optimal regret bound of O~(T)\tilde{O}(\sqrt{T}) for learning optimal policy.

The paper analyzes CMDPs, balancing exploration and exploitation to avoid constraint violations.

problem Balancing exploration and exploitation in CMDPs to satisfy constraints.
method Two approaches: optimistic planning and incremental updates of primal and dual variables.
result Both approaches achieve sublinear regret on utility and constraint violations, with stronger guarantees for the linear programming approach.

Paper proposes a framework for reliable off-policy evaluation in reinforcement learning.

problem Quantifying uncertainty in off-policy estimates for safe deployment of target policies.
method Distributionally robust optimization for creating confidence bounds.
result Non-asymptotic and asymptotic guarantees for robust cumulative reward estimates.

New algorithm for reinforcement learning in uncertain environments with unknown thresholds.

problem Safety in reinforcement learning in unknown and uncertain environments.
method Growing-Window estimator sampling and Stochastic Pessimistic-Optimistic Thresholding (SPOT) algorithm.
result Achieves sublinear regret and constraint violation of ildeO(T) ilde{\mathcal{O}}(\sqrt{T}).

Adversarial CBO optimizes under interventions by adversaries and non-stationarities.

problem Optimizing in the presence of adversaries and non-stationary factors.
method Formalizes CBO as ACBO, introduces CBO-MW algorithm combining online learning and causal modeling.
result First algorithm with bounded regret for ACBO, achieving superior performance in synthetic and real-world environments.

This paper introduces a set of algorithms for Monte-Carlo Bayesian reinforcement learning. Firstly, Monte-Carlo estimation of upper bounds on the Bayes-optimal value function is employed to construct an optimistic policy. Secondly, gradient-based algorithms for approximate upper and lower bounds are introduced. Finally…

2013-03-11abs ↗pdf ↗

New algorithm explores reinforcement learning with noisy data.

problem Exploration in reinforcement learning with complex value functions.
method Randomized exploration with i.i.d. scalar noises and optimistic reward sampling.
result Achieves worst-case regret bound of O~(poly(dEH)T)\widetilde{O}(\mathrm{poly}(d_EH)\sqrt{T}).

The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths. In this work, we propose a family of estimates based on the order statistics over the path ensemble, which allows one to flexibly drive the learning process, towards or agains…

2019-09-15abs ↗pdf ↗