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

50101151201 · May 202619922001200920172026
48 results for recovering rewards

Adversarial RL recovers agent rewards from financial market data simulations.

problem Recovering agent rewards in volatile financial markets with unknown dynamics.
method Adversarial inverse reinforcement learning in latent space simulations.
result Adversarial RL can robustly recover agent rewards from latent space representations of real market data.

This paper solves inverse reinforcement learning with options framework.

problem Reinforcement learning in complex environments with expert demonstrations.
method Gradient method for parametrized options, deducing Q-feature and reward feature spaces, optimal reward function selection.
result Recovered rewards provide effective solution to IRL problem and accelerate transfer learning.

Paper tackles robustness in reward learning with partial identifiability.

problem Partial identifiability in reward learning leads to unreliable target reward recovery.
method Introduces a robust approach to maximize performance with respect to the worst-case reward in the feasible set.
result Develops Rob-ReL, an algorithm that maximizes performance under worst-case identifiability conditions.

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

A significant challenge for the practical application of reinforcement learning in the real world is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this challenge by instead inferring a reward function from expert behavior. While appealin…

2018-05-31abs ↗pdf ↗

A new method recovers rewards from behavior policies using classification and regression.

problem Recovering meaningful rewards from observed behavior in reinforcement learning.
method GenPQR, a modular procedure that estimates behavior policy, evaluates soft Q-function, and recovers normalized reward using classification and regression.
result GenPQR matches or improves reward recovery compared to DeepPQR, while being simpler and more modular.

The goal of the inverse reinforcement learning (IRL) problem is to recover the reward functions from expert demonstrations. However, the IRL problem like any ill-posed inverse problem suffers the congenital defect that the policy may be optimal for many reward functions, and expert demonstrations may be optimal for man…

2019-05-21abs ↗pdf ↗

PQR estimates reward functions from actions and states without assuming state-only rewards.

problem Estimating reward functions from actions and states without state-only assumptions.
method Deep learning approach that sequentially estimates policy, Q-function, and reward.
result PQR uniquely recovers true reward with known transitions and bounds error with unknown transitions.

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.

AIRL learns robust, generalizable reward functions from demonstrations.

problem Learning robust reward functions from demonstrations for changing environments.
method Adversarial Inverse Reinforcement Learning (AIRL) with hierarchical disentangled rewards.
result Generalizable policies and comparable results to state-of-the-art methods.

Imitation Learning describes the problem of recovering an expert policy from demonstrations. While inverse reinforcement learning approaches are known to be very sample-efficient in terms of expert demonstrations, they usually require problem-dependent reward functions or a (task-)specific reward-function regularizatio…

2019-06-19abs ↗pdf ↗

This paper introduces a new reward shaping method for average-reward reinforcement learning.

problem Speeding up convergence to an optimal policy in average-reward reinforcement learning tasks.
method Developed a temporal logic-based approach to automatically generate reward shaping functions.
result The optimal policy can be recovered using the proposed reward shaping framework.

Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification. Finding a set of reward functions to properly guide agent behaviors is particularly challenging in multi-agent scenarios. Inverse reinforcement learning provides a framework to automatically acquire suitable reward functions…

2019-07-30abs ↗pdf ↗

New framework recovers reward and rationality parameters from game behavior.

problem Statistical ambiguity in identifying reward and rationality parameters in competitive games.
method Blind Inverse Game Theory (Blind-IGT) using entropy-regularized Quantal Response Equilibrium and Normalized Least Squares (NLS) estimator.
result Optimal convergence rate of O(N1/2)\mathcal{O}(N^{-1/2}) for joint parameter recovery.

Mitigates biases in reward models using variational inference.

problem Spurious correlations in reward models that align large language models with human preferences.
method Formulates data-generating process, identifies non-spurious latent variables, and uses variational inference to recover them.
result Effective mitigation of spurious correlation issues, yielding more robust reward models.

The study analyzes how neural reward models learn features for policy optimization in a Gaussian single-index model.

problem Reward modeling in policy optimization and its impact on downstream value.
method Two-stage neural reward model: first learns hidden direction, then fits readout layer.
result For any feature-learning temperature above a dimension-free threshold, a constant fraction of neurons recover the hidden direction.

New method uses explicit human demonstrations to teach missing features in reward learning.

problem Reward learning methods rely on handcrafted features, limiting their ability to adapt to new or unexplained corrections.
method Introduces human input guiding the robot from states with missing features to states without, teaching the feature explicitly and integrating it into the reward function.
result Decreases sample complexity and improves generalization of the learned reward over deep IRL baseline.

Inverse optimal control, also known as inverse reinforcement learning, is the problem of recovering an unknown reward function in a Markov decision process from expert demonstrations of the optimal policy. We introduce a probabilistic inverse optimal control algorithm that scales gracefully with task dimensionality, an…

2012-06-18abs ↗pdf ↗

Develops statistical framework for resolving reward function ambiguity in inverse reinforcement learning.

problem Non-uniqueness of reward functions in inverse reinforcement learning.
method Entropy regularization combined with least-squares reconstruction of the reward from the soft Bellman residual.
result Least-squares reward function is unique and consistent with the expert policy.

The paper addresses human-like decision-making in multi-agent systems using bounded risk-sensitive Markov Games.

problem Modeling human-like decision-making in multi-agent systems with risk-seeking and loss-aversion behaviors.
method Forward policy design and inverse reward learning with iterative reasoning and cumulative prospect theory.
result The proposed algorithms demonstrate both risk-averse and risk-seeking behaviors in multi-agent systems.

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.

This work improves transferability of rewards inferred from expert demonstrations.

problem Transferability of rewards inferred from expert demonstrations under limited access to the expert's policy.
method Proposed principal angles as a measure of similarity and dissimilarity between transition laws. Established sufficient conditions for transferability under limited access.
result Two key results on sufficient conditions for transferability to any and local changes in transition laws.

Study experiment planning with function approximation in contextual bandit problems.

problem Designing effective data collection strategies in settings with limited rewards.
method Proposes two experiment planning strategies compatible with function approximation.
result Eluder planning and sampling procedure achieves optimality guarantees.

In this paper, we formalise order-robust optimisation as an instance of online learning minimising simple regret, and propose Vroom, a zero'th order optimisation algorithm capable of achieving vanishing regret in non-stationary environments, while recovering favorable rates under stochastic reward-generating processes.…

2019-10-09abs ↗pdf ↗

Novel algorithm reduces computational burden in IRL with finite-time guarantees.

problem Efficiently recover reward function and optimal policy from expert behavior.
method Single-loop algorithm that maximizes likelihood after each policy improvement step.
result Algorithm provably converges to a stationary solution with finite-time guarantees.

Unified approach to time-inconsistent problems with distribution-dependent rewards.

problem Time-inconsistent problems with distribution-dependent rewards in behavioral finance and economics.
method Equilibrium master equation on Wasserstein space, refined derivatives, Itô's formula.
result Unified approach to find equilibrium solutions for time-inconsistent problems.

We consider the classical problem of sequential resource allocation where a decision maker must repeatedly divide a budget between several resources, each with diminishing returns. This can be recast as a specific stochastic optimization problem where the objective is to maximize the cumulative reward, or equivalently …

2019-02-12abs ↗pdf ↗

We study the recovering bandits problem, a variant of the stochastic multi-armed bandit problem where the expected reward of each arm varies according to some unknown function of the time since the arm was last played. While being a natural extension of the classical bandit problem that arises in many real-world settin…

2019-10-31abs ↗pdf ↗

Algorithm learns diffusion processes with high-dimensional state spaces.

problem Stochastic control of unbounded diffusion processes with high-dimensional state spaces.
method Adaptive partitioning and learning algorithm that refines discretization based on estimation bias and statistical confidence.
result Established regret bounds that depend on problem parameters, extending to unbounded diffusion processes.

Algorithm tackles adaptive discretization in adversarial Lipschitz bandits for dynamic pricing and auctions.

problem Adaptive discretization in adversarial Lipschitz bandits.
method Adversarial Zooming algorithm for adaptive discretization.
result First algorithm for adversarial Lipschitz bandits with instance-dependent regret bounds.

FSPO optimizes synthetic preferences for LLM personalization.

problem Personalizing large language models for diverse users.
method FSPO reframes reward modeling as a meta-learning problem, using few labeled preferences and synthetic data.
result FSPO achieves high winrates in personalized responses, both synthetic and real.

New method for linear bandits with unknown sparsity, improving sparse regret bounds.

problem Sparse regret bounds for unknown sparsity and adversarial action sets.
method Combines online to confidence set conversions with randomized model selection over nested confidence sets.
result First sparse regret bounds for unknown sparsity and adversarial action sets.

New method decomposes Markov chain rewards into persistent and transient components.

problem Ambiguity in classical evaluation methods for Markov chains with reducible and periodic states.
method Minimal exact quotient by the real peripheral invariant subspace, decomposing rewards into persistent and transient components.
result Exact comparison with classical methods shows that the new decomposition reallocates the same information, making persistent modes explicit.