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.

168,695 papers · 148 categories

Trend · papers per month

149298446595 · Jun 202019922001200920172026
48 results for restricted policy classes

New kk-step policy gradient method avoids local optima in restricted policy classes.

problem Suboptimal local optima in policy gradient methods for restricted policy classes.
method Proposes a kk-step policy gradient method to escape myopic local optima.
result The method converges to near optimal solutions exponentially close to the optimal deterministic policy.

Paper proposes a policy gradient method for confounded POMDPs.

problem Estimating policy gradients for confounded POMDPs with continuous state and observation spaces.
method Developed a novel identification result to estimate policy gradients using offline data, solved conditional moment restrictions, and applied min-max learning with function approximation.
result Showed global convergence of the proposed algorithm in finding the optimal policy.

We address the problem of finding an optimal policy in a Markov decision process under a restricted policy class defined by the convex hull of a set of base policies. This problem is of great interest in applications in which a number of reasonably good (or safe) policies are already known and we are only interested in…

2018-02-26abs ↗pdf ↗

This paper optimizes off-policy evaluation in reinforcement learning with function approximation.

problem Estimating cumulative value of a new policy from logged data generated by an unknown policy.
method Regression-based fitted Q iteration method, equivalent to estimating conditional mean embedding of transition operator.
result The method is minimax-optimal, with nearly minimal estimation error.

Revel tackles safe exploration in RL with verified symbolic policies.

problem Computational infeasibility of verifying neural networks in RL learning loops.
method Two policy classes: neurosymbolic with approximate gradients and symbolic policies for efficient verification. Mirror descent over policies to safely update and project policies.
result Revel discovers policies that outperform prior approaches to verified exploration.

New algorithm reduces best-in-class regret in contextual bandits.

problem Compete with the best policy in a class without model restrictions.
method Proposes an algorithm that updates policies by minimizing a pessimistic objective, including a clipped inverse-propensity estimate and variance penalty.
result Achieves fast best-in-class regret rates, including polylogarithmic rates in the parametric case.

Unified framework for risk-aware policy learning in contextual bandits.

problem Optimizing decision rules in high-stakes domains with adverse outcomes.
method Distributional framework for Lipschitz-continuous risk functionals, with novel empirical concentration inequalities.
result Data-dependent suboptimality bounds with an ildeO(1/n) ilde{\mathcal{O}}(1/\sqrt{n}) rate, matching risk-neutral offline policy optimization.

Deep neural networks can estimate Q-values efficiently on low-dimensional state-action spaces.

problem Estimating the performance of a reinforcement learning policy using data from a different policy.
method Deep fitted Q-evaluation method leveraging manifold structure and convolutional neural networks.
result Sharp error bound for fitted Q-evaluation depends on intrinsic dimension and function space mismatch.

DPDP combines neural heuristics with DP for vehicle routing problems.

problem Vehicle routing problems with large scale.
method Deep Policy Dynamic Programming (DPDP) that uses a neural network policy to prioritize and restrict the DP state space.
result DPDP improves upon classical DP algorithms and outperforms neural approaches for TSP, VRP, and TSPTW.

We study the problem of offline policy optimization in stochastic contextual bandit problems, where the goal is to learn a near-optimal policy based on a dataset of decision data collected by a suboptimal behavior policy. Rather than making any structural assumptions on the reward function, we assume access to a given …

2023-09-27abs ↗pdf ↗

In many settings, a decision-maker wishes to learn a rule, or policy, that maps from observable characteristics of an individual to an action. Examples include selecting offers, prices, advertisements, or emails to send to consumers, as well as the problem of determining which medication to prescribe to a patient. Whil…

2018-10-10abs ↗pdf ↗

Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to errors introduced by extrapolation, standard off-policy deep reinforcement learn…

2018-12-07abs ↗pdf ↗

Study improves off-policy evaluation from non-i.i.d. bandit samples.

problem Improving off-policy evaluation from non-independent bandit samples.
method Constructing an estimator from a standardized martingale difference sequence.
result Proposed estimator performs better than existing methods.

This paper investigates a class of attacks targeting the confidentiality aspect of security in Deep Reinforcement Learning (DRL) policies. Recent research have established the vulnerability of supervised machine learning models (e.g., classifiers) to model extraction attacks. Such attacks leverage the loosely-restricte…

2019-06-03abs ↗pdf ↗

We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution. That is, given the capacity to reset the state with those corresponding to the agent's past observations, we help exploration by promoting faster state-space coverage via restarting the agent from a mo…

2018-11-27abs ↗pdf ↗

New MARL algorithms resolve the curse of multiagency with function approximation.

problem Challenges in Multi-Agent Reinforcement Learning (MARL) due to the curse of multiagency.
method V-Learning with Policy Replay and Decentralized Optimistic Policy Mirror Descent.
result First polynomial sample complexity results for learning approximate Coarse Correlated Equilibria (CCEs) of Markov Games under decentralized linear function approximation.

This work tackles learning Markov games with adversarial opponents and achieves both average reward and exploitation.

problem Achieving both average reward and exploiting adaptive opponents in Markov games.
method Develops efficient algorithms and proves hardness results for learning Markov games with adversarial opponents.
result Achieves K\sqrt{K}-regret bounds for certain conditions on opponent policies, complemented by an exponential lower bound.

New algorithm reduces policy regret in tallying bandits.

problem Measuring online learning performance against adaptive adversaries.
method Tallying bandit model, efficient algorithm with complete policy regret guarantee.
result Achieves a complete policy regret guarantee of ildeO(mKT) ilde{\mathcal{O}}(mK\sqrt{T}).

New policy combines Thompson sampling with best challenger rule for best arm identification.

problem Best arm identification in bandit framework with fixed confidence.
method Combines Thompson sampling with best challenger rule.
result Asymptotically optimal for any two-armed bandit problems, near optimal for general K-armed bandit problems.

Proximal policy optimization (PPO) is one of the most successful deep reinforcement-learning methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, its optimization behavior is still far from being fully understood. In this paper, we show that PPO could neither strictly restr…

2019-03-19abs ↗pdf ↗

This paper tackles data-efficient nonlinear control in Hamiltonian systems using symplectic geometry.

problem Data-efficient nonlinear control in Hamiltonian systems.
method Combines symplectic geometry, recurrence on energy level sets, and chain policies to solve target reachability problems.
result Data requirements depend on geometric and recurrence properties of the Hamiltonian, not the state dimension.

KBB algorithm reduces sample complexity for policy evaluation in general state spaces.

problem Policy evaluation in large state spaces with high sample complexity.
method Alternates between fitting Bellman residual and estimating value function via adaptive feature set growth.
result Super-linear convergence rates demonstrated, with reductions in sample complexity.

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.

This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. (2009) exhibit a policy such that with probability at least 1-1/n, the regret of the policy is of order log(n). They have also shown that such a …

2011-07-22abs ↗pdf ↗

SAVO actor improves reinforcement learning by avoiding local optima in complex Q-functions.

problem Gradient ascent in complex Q-functions leads to suboptimal solutions.
method SAVO actor generates multiple action proposals and truncates poor local optima.
result SAVO actor finds optimal actions more frequently and outperforms other architectures.

Study shows TD(0) with linear approx. converges for reversible Markov chains.

problem TD(0) divergence with off-policy and function approximation.
method Analyzes standard TD(0) with reversible Markov chains, adapting stochastic approximation framework.
result Establishes convergence with probability one for projected Bellman error = 0.

A new algorithm uses IVs to learn optimal policies from observational data.

problem Learning optimal policies from unobserved variable confounded data.
method IV-aided Value Iteration (IVVI) algorithm based on conditional moment restrictions.
result First provably efficient algorithm for instrument-aided offline RL.

Many real world tasks exhibit rich structure that is repeated across different parts of the state space or in time. In this work we study the possibility of leveraging such repeated structure to speed up and regularize learning. We start from the KL regularized expected reward objective which introduces an additional c…

2019-05-03abs ↗pdf ↗

Batch Reinforcement Learning (RL) algorithms attempt to choose a policy from a designer-provided class of policies given a fixed set of training data. Choosing the policy which maximizes an estimate of return often leads to over-fitting when only limited data is available, due to the size of the policy class in relatio…

2014-05-12abs ↗pdf ↗

Many reinforcement learning applications involve the use of data that is sensitive, such as medical records of patients or financial information. However, most current reinforcement learning methods can leak information contained within the (possibly sensitive) data on which they are trained. To address this problem, w…

2019-02-01abs ↗pdf ↗

We study numerical restricted volumes of (1,1) classes on compact Kahler manifolds, as introduced by Boucksom. Inspired by work of Ein-Lazarsfeld-Mustata-Nakamaye-Popa on restricted volumes of line bundles on projective manifolds, we pose a natural conjecture to the effect that irreducible components of the non-Kahler …

2016-08-25abs ↗pdf ↗

Develops a new trading strategy for statistical arbitrage with path-dependent signals.

problem Optimal execution in statistical arbitrage strategies with dynamic predictive signals.
method Signature-based framework modeling alpha and trading speed as linear functionals of truncated signature of market path.
result Fitted policy achieves higher return on turnover compared to a z-score benchmark.

Paper develops methods for inference on time series data using neural networks and sieves.

problem Inference on time series data with nonparametric conditional moment restrictions.
method GN-QLR based inference using general nonlinear sieves and multilayer neural networks.
result Optimally weighted GN-QLR statistic is asymptotically Chi-square distributed.

Optimistic NPG improves policy optimization in online RL with efficient sample complexity.

problem Limited theoretical understanding of policy optimization, especially in online RL.
method Combines natural policy gradient with optimistic policy evaluation.
result Achieves optimal dimension dependence sample complexity for learning near-optimal policies.

Proposes Constrained Q-learning for reinforcement learning with constraints.

problem Optimizing multiple objectives while adhering to constraints in reinforcement learning.
method Directly restricts the action space in Q-update to learn optimal Q-function for constrained MDP.
result Improves safety and optimality in high-level decision making for autonomous driving.

Paper addresses offline policy evaluation in RL, achieving near-optimal bounds for various policy classes.

problem Evaluate all policies in a class simultaneously for offline RL.
method Uniform convergence in OPE for various policy classes, achieving optimal episode complexity.
result Achieves optimal episode complexity of O(H^3/d_mε^2) for identifying ε-optimal policies.

We introduce Implicit Policy, a general class of expressive policies that can flexibly represent complex action distributions in reinforcement learning, with efficient algorithms to compute entropy regularized policy gradients. We empirically show that, despite its simplicity in implementation, entropy regularization c…

2018-06-10abs ↗pdf ↗