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.
Reward tweaking optimizes behavior for long-term goals by adjusting the reward function.
problem Optimizing behavior for long-term goals in reinforcement learning with unstable long planning horizons.
method Reward tweaking learns a surrogate reward function that induces optimal behavior for the original task.
result Reward tweaking guides agents towards better long-term returns while planning for short horizons.
AlphaZero's reward function is replaced with a total ordering, enabling self-play without balancing.
problem Learning optimal play in games without explicit reward balancing.
method Modified AlphaZero algorithm using only a total ordering of game outcomes.
result Comparable optimal play learned in a similar time frame without balancing.
Reinforcement learning mimics expert behavior.
problem Learning from expert demonstrations in reinforcement learning.
method Reduction to reinforcement learning with a stationary reward.
result Expert reward can be recovered and imitation learning is bounded.
Unified theory for UCB policies in total and max bandit problems.
problem Order optimality of UCB policies in max bandit problems.
method Unified definition of UCB policy using oracle quantity and failure count.
result UCB policies are order optimal in both total and max bandit problems.
Optimizing rewards under budget constraints with correlated costs and rewards.
problem Maximizing total expected reward under a budget constraint on total cost with correlated and potentially heavy-tailed cost-reward pairs.
method Proposes algorithms exploiting correlation between cost and reward via linear minimum mean-square error estimation to achieve tight regret bounds.
result Achieves O ( log B ) O(\log B) O ( log B ) regret for a budget B > 0 B>0 B > 0 under certain moment conditions. Contextual bandits are online learners that, given an input, select an arm and receive a reward for that arm. They use the reward as a learning signal and aim to maximize the total reward over the inputs. Contextual bandits are commonly used to solve recommendation or ranking problems. This paper considers a learning s…
Algorithm maximizes total reward in multi-agent bandits with adversarial corruptions.
problem Maximizing total reward in multi-agent bandits with adversarial corruptions.
method Proposes a cooperative learning algorithm robust to adversarial corruptions.
result Demonstrates an additive O ( ( L / L min ) C ) O((L / L_{\min}) C) O (( L / L m i n ) C ) regret term for an adversary with unknown corruption budget. New method reduces total cost constraints in CBwK to sqrt(T) with fairness application.
problem Maximize rewards while adhering to total cost constraints in CBwK.
method Dual strategy based on projected-gradient-descent updates.
result Total cost constraints reduced to sqrt(T) with poly-logarithmic terms.
Adaptive KL-UCB algorithm for Markov and i.i.d. rewards.
problem Regret minimization for Markovian and i.i.d. rewards in MAB problems.
method Identifies Markovian vs. i.i.d. rewards, switches between KL-UCB variants.
result Logarithmic regret for both i.i.d. and Markovian settings.
Algorithm tackles clustered contextual bandits with resource constraints.
problem Maximizing reward while respecting resource limits in unknown cluster contexts.
method Combines econometrics and bandit constraints techniques for sublinear regret.
result Achieves sublinear regret without needing all arm information.
Contextual bandits study how reward variance affects regret bounds.
problem Investigating how small reward variance impacts regret bounds in contextual bandits.
method Analyzing two types of adversaries and function approximation complexities.
result Regret bounds are influenced by the eluder dimension and reward variance.
Attackers can significantly reduce team rewards in cooperative multi-agent reinforcement learning.
problem Robustness of cooperative multi-agent reinforcement learning to adversaries.
method Novel attack method involving training a policy network and using targeted adversarial examples.
result Reduces team reward from 20 to 9.4 by attacking a single agent, reducing winning rate from 98.9% to 0%.
Text generation is a crucial task in NLP. Recently, several adversarial generative models have been proposed to improve the exposure bias problem in text generation. Though these models gain great success, they still suffer from the problems of reward sparsity and mode collapse. In order to address these two problems, …
A new UCB policy improves reward-cost ratio estimation in budgeted MAB.
problem Maximizing reward-cost ratio under budget constraints.
method ω-UCB policy with asymmetric confidence intervals.
result Logarithmic regret and superior performance in various settings.
We consider the linear contextual bandit problem with resource consumption, in addition to reward generation. In each round, the outcome of pulling an arm is a reward as well as a vector of resource consumptions. The expected values of these outcomes depend linearly on the context of that arm. The budget/capacity const…
This paper studies poisoning attacks in episodic RL and discovers their effectiveness depends on reward bounds.
problem Understanding security threats to RL algorithms through poisoning attacks.
method Examined two types of poisoning attacks: reward and action manipulation, in bounded and unbounded reward settings.
result The effectiveness of poisoning attacks depends on reward bounds, with different attack costs and success rates.
OP-GFNs sample candidates in order-preserving proportion to a learned reward function.
problem Sampling diverse candidates with varying rewards in multi-objective optimization.
method Order-Preserving GFlowNets (OP-GFNs) use a learned reward function consistent with a provided order on candidates.
result Training OP-GFNs sparsifies the reward landscape, focusing on higher-ranked candidates.
The multi-armed bandit (MAB) problem is a classic example of the exploration-exploitation dilemma. It is concerned with maximising the total rewards for a gambler by sequentially pulling an arm from a multi-armed slot machine where each arm is associated with a reward distribution. In static MABs, the reward distributi…
New MAB model incentivizes user arm-pulling with self-reinforcing preferences.
problem Balancing exploration and exploitation in recommender systems with incentivized user preferences.
method Proposes a new MAB model with random arm selection and two policies: At-Least- n n n Explore-Then-Commit and UCB-List. result Achieves O ( l o g T ) O(log T) O ( l o g T ) expected regret and O ( l o g T ) O(log T) O ( l o g T ) expected payment over a time horizon T T T . New insights into balancing reward and fairness in stochastic MAB.
problem Balancing reward and fairness in stochastic multi-armed bandits.
method Formulated a penalization framework and proposed a hard-threshold UCB-like algorithm.
result Asymptotic fairness, nearly optimal regret, better reward-fairness tradeoff.
New algorithm for RL with horizon-free reward-free exploration for linear MDPs.
problem Reward-free reinforcement learning with long planning horizons.
method Uncertainty-weighted value-targeted regression with exploration-driven pseudo-reward and moment estimator.
result Horizon-free sample complexity of O ( d 2 ε − 2 ) O(d^2\varepsilon^{-2}) O ( d 2 ε − 2 ) for finding an ε \varepsilon ε -optimal policy. The stochastic multi-armed bandit (MAB) problem is a common model for sequential decision problems. In the standard setup, a decision maker has to choose at every instant between several competing arms, each of them provides a scalar random variable, referred to as a "reward." Nearly all research on this topic consider…
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 …
A new algorithm for offline RL with trajectory-wise reward reduces bias and variance errors.
problem Offline RL with trajectory-wise reward incurs large bias and variance errors.
method PARTED algorithm that decomposes trajectory return into proxy rewards and performs pessimistic value iteration.
result PARTED achieves provably efficient suboptimality bounds in general MDPs with trajectory-wise reward.
Proposes BSI for valid statistical inference on bandit algorithms.
problem Valid statistical inference on bandit algorithms' performance.
method Fits a simulator of the bandit environment from observed data and uses it to estimate mean reward under any policy.
result Proves asymptotically valid confidence intervals and maintains nominal coverage.
A multi-player bandit system resists adversarial attacks with near-optimal regret.
problem Adversaries attempt to manipulate rewards in a multi-player multi-armed bandit game.
method Players communicate a single bit to resist attacks, achieving near-optimal regret.
result Achieves near-optimal regret of O ( log 1 + δ T + W ) O(\log^{1+δ}T + W) O ( log 1 + δ T + W ) , where W W W is the total time of adversarial attacks. Adaptive policies solve a linear program to maximize rewards while minimizing costs in sales with discounts.
problem Maximizing rewards in sales with discounts while considering costs.
method Solves a linear program based on upper-confidence estimates of conversion probabilities.
result Achieves a regret bound of the typical order (OPT/ B B B ) T \sqrt{T} T , where B is the total budget allowed. New algorithm optimizes reward while ensuring safety in complex decision-making problems.
problem Maximizing reward while adhering to safety constraints in complex decision-making problems.
method Optimistic Primal-Dual Proximal Policy Optimization (OPDOP) algorithm combining least-squares policy evaluation and a bonus term for safe exploration.
result Achieves i l d e O ( d H 2.5 T ) ilde{O}(d H^{2.5}\sqrt{T}) i l d e O ( d H 2.5 T ) regret and i l d e O ( d H 2.5 T ) ilde{O}(d H^{2.5}\sqrt{T}) i l d e O ( d H 2.5 T ) constraint violation. New algorithms for efficient learning with long-term rewards in contextual bandits.
problem Efficient learning with long-term rewards in contextual bandits.
method Proposes new algorithms leveraging sparsity to discover dependence patterns and arm parameters.
result Regret upper bounds for data-poor and data-rich regimes, showing improved sample complexity.
A novel algorithm reduces communication costs in federated best arm identification.
problem Identifying the best arm in a federated multi-armed bandit setup with minimal communication cost.
method Proposes a novel algorithm called FedElim that communicates only in exponential time steps.
result Demonstrates that communication is almost cost-free in FedElim, with a total cost at most 3 times the maximum under its variant.
Optimal algorithm for maximizing rewards in contextual bandits with resource constraints.
problem Maximizing rewards in contextual bandits with resource constraints.
method Proposed a universal and optimal algorithmic framework for CBwK by reducing it to online regression.
result Established the optimality of the proposed algorithm for various function classes.
We propose and study the known-compensation multi-arm bandit (KCMAB) problem, where a system controller offers a set of arms to many short-term players for T T T steps. In each step, one short-term player arrives to the system. Upon arrival, the player aims to select an arm with the current best average reward and receiv…
New algorithm learns optimal policy for average reward MDPs with sample complexity matching lower bound.
problem Learning optimal policy for average reward in uniformly ergodic MDPs.
method Developed an estimator with sample complexity of O(|S||A|t_{mix}ε^{-2}).
result First algorithm to match lower bound of existing literature.
New algorithm tackles adversarial corruption in Lipschitz bandits with sub-linear regret.
problem Adversarial corruption in Lipschitz bandits.
method Developed robust Lipschitz bandit algorithms for weak and strong adversaries.
result Achieved sub-linear regret under both weak and strong adversaries.
New algorithm reduces regret and constraint violation in constrained bandit problems.
problem Optimizing under budget and stochastic constraints in resource-constrained settings.
method Lyapunov optimization methodology, t L y O n { t LyOn} t L y O n algorithm. result Achieves O ( K B log B ) O(\sqrt{K B\log B}) O ( K B log B ) regret and zero constraint-violation for large B B B . In this paper, we propose a methodology based on piece-wise homogeneous Markov chain for credit ratings and a multivariate model of the credit spreads to evaluate the financial risk in European Union (EU). Two main aspects are considered: how the financial risk is distributed among the European countries and how large …
HAMLET optimizes algorithm selection for machine learning tasks.
problem Limited time budgets and computational resources make traditional bandit approaches ineffective for automated algorithm selection.
method HAMLET incorporates learning curve extrapolation and time-awareness to select machine learning algorithms.
result HAMLET variants outperform other bandit-based strategies in experiments with recorded hyperparameter tuning traces.
This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast time constant limit of leaky integrate-and-fire neurons equipped with spiking timing dependent plasticity (STDP) and (ii) is amenable to the…
New algorithms boost SAT solver performance by optimizing restart strategies.
problem Optimizing decision-making under time constraints with restarts.
method Developed online learning algorithms for a bandit problem with controlled restarts.
result Achieved O ( log ( τ ) ) O(\log(τ)) O ( log ( τ )) and O ( τ log ( τ ) ) O(\sqrt{τ\log(τ)}) O ( τ log ( τ ) ) regret bounds. Paper develops robust estimators and strategies for stochastic MABs with heavy-tailed rewards.
problem Stochastic multi-armed bandits with heavy-tailed rewards.
method Proposes a novel robust estimator and perturbation-based exploration strategy.
result Develops upper and lower regret bounds for various perturbations.
Investigates risk measures for DC pension decumulation.
problem Develop optimal decumulation strategies for DC plan holders.
method Formulates decumulation as a control problem, studies risk measures (expected shortfall, linear shortfall, probability of shortfall).
result Optimal controls for expected reward and expected shortfall are identical to those for expected reward and linear shortfall.
Algorithm improves movie recommendation efficiency with fairness constraints.
problem Improving movie recommendation efficiency with fairness constraints in combinatorial semi-bandits.
method Adopted Thompson Sampling with beta priors and Bernoulli likelihoods to handle fairness constraints.
result Time-averaged regret upper bounded by $\frac{N}{2η} + O\left(\frac{\sqrt{mNT\ln T}}{T}
ight)$ , with fairness constraints satisfied.
Logarithmic regret strategies for safe multi-armed bandits with safety risk constraints.
problem Maximizing reward while avoiding unsafe arms under safety risk constraints.
method Doubly optimistic strategies with pseudo-regret formulation.
result Logarithmic regret bounds for safe multi-armed bandits.
Improved best-arm identification in correlated multi-armed bandits.
problem Best-arm identification in multi-armed bandits with correlated rewards.
method Proposed C-LUCB algorithm that exploits upper bounds on conditional rewards.
result Significant reduction in sample complexity for best-arm identification.
New algorithm for non-stationary bandits with slow drifts.
problem Minimizing dynamic regret in non-stationary bandits with slowly varying rewards.
method Extends Successive Elimination to non-stationary bandits with a novel gap profile characterization.
result First instance-dependent regret upper bound for slowly varying non-stationary bandits.
New algorithm identifies good arms with fewer samples when thresholds are close.
problem Good arm identification in bandit problems with small threshold gaps.
method Proposes lil'HDoC algorithm to improve GAI under small threshold gaps.
result Sample complexity of first λ output arm is nearly identical to HDoC algorithm when thresholds are close.
Stable GFlowNets prevent loss spikes and mode collapse in training.
problem Unstable training of GFlowNets leading to loss spikes and mode collapse.
method Assessed sensitivity of GFlowNet objectives, derived loss-to-TV bounds, and proposed Stable GFlowNets.
result Stable GFlowNets improve training behavior and distributional fidelity.