Study optimal reward schemes for inducing desired player performance in risky contests.
problem Designing optimal rewards to encourage desired performance levels in risky contests.
method Analyzed the optimal reward schemes for inducing average and specific rank performance.
result Optimal reward schemes can have surprising shapes, not just related to inequality.
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show that a potential-based reward shaping scheme is able to preserve optimality of stochastic policies, and demonstrate that the ability of an a…
The paper proposes a model reward scheme for collaborative ML based on Shapley value and information gain.
problem Designing fair incentives for collaborative machine learning.
method The paper proposes a reward scheme based on Shapley value and information gain, with properties like fairness and stability.
result The proposed reward scheme satisfies fairness and trade-offs between desirable properties via an adjustable parameter.
Adaptive exploration scheme for evaluating multiple policies with different rewards.
problem Online multi-reward multi-policy evaluation.
method Adapted ( ε , δ ) (ε,δ) ( ε , δ ) -PAC perspective and MR-NaS exploration scheme to minimize sample complexity. result Demonstrated effectiveness of adaptive exploration in tabular domains.
New algorithm finds optimal policies without knowing reward functions.
problem Reward-agnostic exploration in reinforcement learning.
method Designs an algorithm that explores without reward information, achieving minimax optimality.
result Achieves provable minimax optimality in finding optimal policies for multiple reward functions.
Regularized policies are robust to adversarial rewards.
problem Understanding the effects of regularization on policy exploration and robustness.
method Using Fenchel duality to derive the dual problem of the regularized RL objective, showing the optimal policy is robust to adversarial rewards.
result Regularized policies are optimal for a reinforcement learning problem under adversarial reward conditions.
New method for LLMs to learn reasoning by optimizing latent variables.
problem Teaching LLMs to generate logical justifications for answers.
method Formalized reasoning as latent variable model, derived FEM objective, designed sampling schemes.
result Prompt Posterior Sampling (PPS) outperforms other schemes in learning to reason.
One-bit feedback suffices for a bandit problem's optimal strategy.
problem Optimal strategy for multi-armed bandit problem with limited feedback.
method Coding and decoding schemes for one-bit feedback to mimic full-reward feedback.
result Regret ratio approaches 1 with one-bit feedback.
Paper optimizes recommendation systems for long-term business metrics.
problem Short-term reward optimization ignores long-term business metrics.
method Introduced a framework for modeling long-term rewards in RecoGym.
result Proposed a simple extension leading to state-of-the-art results.
Reward collapse occurs when ranking-based reward models yield uniform rewards for different prompts.
problem Reward collapse in aligning large language models with human preferences.
method Introduced a prompt-aware optimization scheme to derive closed-form expressions for reward distributions.
result Our prompt-aware utility functions significantly alleviate reward collapse during training.
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.
New method tracks shifts in infinite-armed bandits without prior knowledge.
problem Tracking shifts in non-stationary infinite-armed bandits.
method Blackbox conversion of finite-armed MAB to infinite-armed non-stationary, randomized elimination.
result First parameter-free optimal regret bounds for all reservoir regularity regimes.
In this paper, we present a discrete-type approximation scheme to solve continuous-time optimal stopping problems based on fully non-Markovian continuous processes adapted to the Brownian motion filtration. The approximations satisfy suitable variational inequalities which allow us to construct ε ε ε -optimal stopping tim…
RL framework optimizes trading costs in noisy markets.
problem Optimal execution and placement in noisy markets.
method Dual-window Denoise PPO RL network, imitation learning, comprehensive market features, flexible action formulation.
result RL agents outperformed TWAP strategy in execution cost.
New algorithm for reward-free RL with linear function approximation, reducing sample complexity.
problem Efficiently learning optimal policies without prior reward information in complex environments.
method Developed an algorithm for reward-free RL in linear Markov decision processes, proving sample complexity bounds.
result Polynomial sample complexity in feature dimension and planning horizon, independent of states and actions.
We consider the task of Inverse Reinforcement Learning in Contextual Markov Decision Processes (MDPs). In this setting, contexts, which define the reward and transition kernel, are sampled from a distribution. In addition, although the reward is a function of the context, it is not provided to the agent. Instead, the a…
New algorithm for collaborative bandit learning reduces sample complexity and regret.
problem Optimal arm identification in a multi-agent bandit model with communication.
method Phased elimination with data-dependent sampling schemes.
result Near-optimal algorithm for pure exploration in collaborative bandit learning.
A new insurance and reinsurance pricing scheme based on realized loss.
problem Determining fair and risk-adjusted insurance premiums.
method Performance-based variable premium scheme with random initial premium adjusted based on realized loss.
result The variable premium scheme reduces reinsurer's total risk exposure compared to expected-value premium.
New algorithm for multi-player bandits with collision-dependent rewards.
problem Stochastic multi-player multi-armed bandits with collision-dependent reward distributions.
method Error-Correction Collision Communication (EC3) algorithm.
result EC3 algorithm achieves optimal regret approaching centralized MP-MAB regret.
New method for efficient online exploration in RLHF reduces regret.
problem Efficiently collecting new preference data in RLHF to refine reward model and policy.
method Proposes a new exploration scheme that directs preference queries toward reducing uncertainty in reward differences most relevant to policy improvement.
result Establishes regret bounds of order T ( β + 1 ) / ( β + 2 ) T^{(β+1)/(β+2)} T ( β + 1 ) / ( β + 2 ) for online RLHF, with polynomial scaling in all model parameters. This paper optimizes driver repositioning using MARL and reward design for better service and traffic management.
problem Unserved passenger requests due to drivers' cruising behavior during passenger seeking.
method Mean field multi-agent reinforcement learning (MARL) with a reward design scheme and Bayesian optimization (BO) to solve bilevel optimization problems.
result Optimal toll charges and service charges can improve platform and city planner objectives by significant margins, leading to better traffic conditions.
Study on private and robust multi-armed bandits with contaminated heavy-tailed rewards.
problem Private and robust multi-armed bandits with contaminated heavy-tailed rewards.
method Proposed a meta-algorithm with a private and robust mean estimation sub-routine exttt{PRM}.
result Achieved nearly-optimal regret for two heavy-tailed settings.
Improved DPO framework penalizes preference uncertainty to avoid overoptimization.
problem Aligning LLMs to human preferences is challenging due to varied, context-dependent, and ambiguous preferences.
method Developed a pessimistic framework for DPO by introducing preference uncertainty penalization schemes.
result Improved overall performance and better completions on high-uncertainty responses compared to vanilla DPO.
New L 1 L_1 L 1 -Coverage objective simplifies exploration in reinforcement learning.
problem Challenges in exploration for high-dimensional domains.
method Introduces L 1 L_1 L 1 -Coverage objective to enable efficient exploration and planning. result First computationally efficient algorithms for online reinforcement learning with low coverability.
This work optimizes identifying good arms in nonparametric multi-armed bandits.
problem Efficiently identifying arms with high means in nonparametric settings.
method Combining reward-maximizing sampling with a nonparametric sequential test for anytime-valid labeling.
result Achieves minimax optimal stopping times for identifying arms above a threshold.
A scheme robust to action erasures improves MAB performance.
problem Learning in multi-arm bandits with erasure channels.
method Proposes a scheme to work on top of any MAB algorithm.
result Worst-case regret is at most a factor of O ( 1 / 1 − ε ) O(1/\sqrt{1-ε}) O ( 1/ 1 − ε ) away from no-erasure case. Efficiently learns matching rewards in two-sided markets with matrix completion.
problem Learning high-dimensional matching rewards in matching markets with limited data.
method Utilizes matrix completion with a novel approach to handle matching interference.
result Near-optimal guarantees for reward learning under matching interference.
New algorithm LOOP learns infinite-horizon AMDPs efficiently with function approximation.
problem Learning optimal policies in infinite-horizon AMDPs with function approximation.
method LOOP combines model-based and value-based methods with novel confidence sets and policy updating.
result LOOP achieves sublinear regret bound of i l d e O ( p o l y ( d , s p ( V ∗ ) ) T β ) ilde{\mathcal{O}}(\mathrm{poly}(d, \mathrm{sp}(V^*)) \sqrt{Tβ} ) i l d e O ( poly ( d , sp ( V ∗ )) T β ) . Novel approach to contextual bandits using self-supervised learning.
problem Exploiting rich data representations in computer vision without explicit labels.
method Combining contextual bandit objective with self-supervision objective.
result Substantial gains in cumulative reward on computer vision datasets.
This paper presents four different ways of looking at the well-known Least Squares Temporal Differences (LSTD) algorithm for computing the value function of a Markov Reward Process, each of them leading to different insights: the operator-theory approach via the Galerkin method, the statistical approach via instrumenta…
In light of the growing interest in agent-based market models, we bring together several earlier works in which we considered the topic of self-consistent market modelling. Building upon the binary game structure of Challet and Zhang, we discuss generalizations of the strategy reward scheme such that the agents seek to…
Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents. Motivated by decentralized applications such as sensor networks, swarm robotics, and power grids, we study policy evaluation in MARL, where agents with jo…
New algorithm uses Whittle index to improve Q-learning for restless bandits.
problem Optimizing decision-making in multiarmed restless bandits with average reward.
method Introduces a novel reinforcement learning algorithm combining Q-learning and Whittle index policy.
result Demonstrates significant computational gains and excellent empirical performance.
Shaping in humans and animals has been shown to be a powerful tool for learning complex tasks as compared to learning in a randomized fashion. This makes the problem less complex and enables one to solve the easier sub task at hand first. Generating a curriculum for such guided learning involves subjecting the agent to…
SA-GFN corrects biases in GFlowNets due to graph symmetries.
problem Systematic biases in state transition probability computations.
method Incorporates symmetry corrections into the learning process through reward scaling.
result Eliminates need for explicit state transition computations.
New method learns various data manipulation schemes for model training.
problem Improving model training with data manipulation.
method Adapts RL reward learning algorithm for data manipulation learning.
result Significant improvement in classification performance.
Local search improves GFlowNets' ability to generate high-reward samples.
problem GFlowNets struggle with over-exploration in high-reward space.
method Local search focusing on high-reward samples via backtracking and reconstruction.
result Significant performance improvement in biochemical tasks.
Personalized recommendation systems (RS) are extensively used in many services. Many of these are based on learning algorithms where the RS uses the recommendation history and the user response to learn an optimal strategy. Further, these algorithms are based on the assumption that the user interests are rigid. Specifi…
EPIC quantifies reward differences without policy optimization.
problem Distinguishing reward function quality from policy optimization issues.
method EPIC distance to compare reward functions directly.
result EPIC bounds policy training success and regret.
Reward models need more than just accuracy for effective RLHF.
problem The effectiveness of reward models in RLHF is not fully understood.
method An optimization perspective to evaluate reward models.
result Reward models with low reward variance can lead to a flat optimization landscape, hindering performance.
In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the Bellman equation and a fixed point iteration scheme known as the value iteration is u…
New method for optimizing risk in financial models using Fourier transforms.
problem Optimizing risk in financial models with multi-period mean-CVaR.
method Strictly monotone 2D integration scheme via Fourier-trained transition kernels.
result Established robust and accurate optimization method for financial models.
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.
Paper addresses reward hacking in preference optimization, proposing POWER-DL to improve AI alignment.
problem Reward hacking problem in preference optimization, leading to undesired behaviors.
method POWER-DL combines robust reward maximization and dynamic label updates to mitigate reward hacking.
result POWER-DL consistently outperforms state-of-the-art methods on alignment benchmarks.
Paper proposes Langevin dynamics for adaptive IRL of stochastic gradient algorithms.
problem Estimating reward functions from noisy gradient estimates of stochastic gradient agents.
method Generalized Langevin dynamics algorithm for IRL.
result Proposed algorithms asymptotically generate samples proportional to exp(R(θ)).
LinConTS improves regret and constraint violations in probabilistic linearly constrained bandits.
problem Maximizing cumulative reward under probabilistic linear constraints.
method LinConTS, a Thompson Sampling-based algorithm for bandits with linear constraints.
result LinConTS achieves O(log T) regret and constraint violations for suboptimal arms.
Adaptive RL optimizes testing resource allocation for dynamic software environments.
problem Optimizing resource allocation for evolving software testing environments.
method Integrates Q-learning with hybrid reward design for sequential decision-making.
result Consistently outperforms static and optimization-based baselines in simulation studies.
New method for RL with general utilities using variational policy gradient.
problem Optimizing policies with general concave utility functions in RL.
method Derives Variational Policy Gradient Theorem, develops variational Monte Carlo gradient estimation algorithm.
result Global convergence to optimal policy for general objectives, exponential convergence under strong convexity.