Study shows certainty equivalent policy minimizes regret in continuous-time systems.
problem Minimizing regret in continuous-time stochastic linear-quadratic systems.
method Theoretical analysis of randomized certainty equivalent policy.
result Establishes square-root of time regret bounds and linear scaling with parameters.
This paper optimizes MDP policies for efficient state aggregation.
problem Optimizing policies in aggregated Markov chains while preserving optimal performance.
method Homomorphic mappings to establish optimal policy equivalence and derive performance bounds.
result Developed HPG and EBHPG methods for efficient aggregation and policy optimization.
A new RL approach learns near-equivalent actions for healthcare decisions.
problem Finding optimal actions in healthcare settings where actions may be near-equivalent.
method Temporal difference learning with a near-greedy heuristic for action selection.
result The proposed algorithm discovers meaningful near-equivalent actions and converges well.
Study risk-sensitive market making with entropy regularization for better quote control.
problem Risk-sensitive market making with exponential utility and penalties.
method Entropy-regularized certainty-equivalent Bellman policies for discrete-time market dynamics.
result Proves convergence and performance bounds for entropy-regularized policies.
Paper shows equivalence between two alignment methods and introduces a new algorithm.
problem Ensuring human alignment of large language models for useful, safe, and pleasant user experience.
method Introduces IPO-MD algorithm, showing equivalence between IPO and Nash-MD methods.
result Equivalence between IPO and Nash-MD methods proven when considering online version of IPO.
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.
Study bridges welfare maximization and CATE estimation in policy learning.
problem Tackles the gap between empirical welfare maximization and conditional average treatment effect estimation in policy learning.
method Shows equivalence between EWM and least squares over reparameterized policy class, proposes regularization method.
result Both approaches are interchangeable under common conditions and share theoretical guarantees.
The paper introduces a new method for estimating optimal policies in dynamic treatment regimes using information geometry.
problem Estimating optimal policies in dynamic treatment regimes.
method Minimum information divergence method based on γ-power divergence. result The γ-power divergence method effectively seeks the optimal policy by vanishing the divergence between policy-equivalent Q-functions. Quadratic hedging of option payoffs generates the variance optimal martingale measure. When an option features an exercise policy and its cash flows are hedged according to this approach, it may be tempting to optimize such a policy under this measure. Because the variance optimal martingale measure may not be an equiv…
Paper shows equivalence between two dividend preference models.
problem Understanding investor and firm preferences for dividends.
method Formulated Epstein-Zin preference, proved equivalence with Maenhout's model.
result Robust dividend policy is equivalent to a threshold strategy based on surplus process.
Q-learning adapted to find near-equivalent treatment strategies.
problem Finding optimal treatment sequences in dynamic treatment regimes.
method Introducing a worst-value tolerance criterion to find sets of near-equivalent policies.
result Constructs families of near-equivalent treatment strategies.
Deriving and applying Proximal Policy Optimization to GFlowNets for efficient training of discrete sampling policies
problem Training stochastic policies to sample from structured discrete probability distributions
method Deriving policy gradient algorithms for GFlowNets and applying Proximal Policy Optimization
result Improved convergence speed and data efficiency compared to standard GFlowNet training objectives
Solves Merton's investment-consumption problem with certainty equivalent approach.
problem Maximizing CRRA utility of consumption over time and investment mix.
method Identifies a certainty equivalent problem for the Merton problem, reformulates it as an SOCP, and applies it to model predictive control.
result The certainty equivalent problem can be solved as an SOCP, facilitating model predictive control.
Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient policy update. We show that the natural gradient and trust region optimization are equivalent if we use the natural parameterization of a st…
This paper unifies two types of statistical methods for estimating treatment effects.
problem Isolating online A/B-tests and off-policy evaluation.
method Establishes formal equivalence between online Difference-in-Means and off-policy Inverse Propensity Scoring methods.
result Standard online methods are mathematically equivalent to off-policy methods with optimal control variates.
New findings reveal discount regularization can be seen as a strong prior, leading to poor performance in unevenly sampled data.
problem Discount regularization leads to poor performance in unevenly sampled data.
method Equivalence theorem showing discount regularization as a strong prior, setting regularization parameters locally for individual state-action pairs.
result Discount regularization can be seen as a strong prior, leading to poor performance in unevenly sampled data.
Paper introduces RCaI, a risk-sensitive control method using Rényi divergence.
problem Risk-sensitive control in reinforcement learning.
method RCaI extends CaI using Rényi divergence variational inference.
result Risk-sensitive optimal policy can be obtained by solving a soft Bellman equation.
Entropy regularization is an important idea in reinforcement learning, with great success in recent algorithms like Soft Q Network (SQN) and Soft Actor-Critic (SAC1). In this work, we extend this idea into the on-policy realm. We propose the soft policy gradient theorem (SPGT) for on-policy maximum entropy reinforcemen…
We consider a continuous-time model for inventory management with Markov modulated non-stationary demands. We introduce active learning by assuming that the state of the world is unobserved and must be inferred by the manager. We also assume that demands are observed only when they are completely met. We first derive t…
Learning to control robots directly based on images is a primary challenge in robotics. However, many existing reinforcement learning approaches require iteratively obtaining millions of robot samples to learn a policy, which can take significant time. In this paper, we focus on learning a realistic world model capturi…
Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting. However, vanilla online variants are on-policy only and not able to take advantage of off-policy data. In this paper we describe a new technique that combines policy gradient with off-policy Q-learning, drawing experie…
CEFOL uses deep learning for dynamic programming with recursive utility.
problem Challenges in solving dynamic programming problems with recursive utility.
method Introduces a separate neural network for certainty equivalent, uses first-order optimality conditions to learn value and policy functions.
result CEFOL achieves high accuracy in learning value and policy functions, matching VFI benchmarks.
Study risk-sensitive reinforcement learning with optimized certainty equivalents.
problem Risk-sensitive reinforcement learning in finite discounted MDPs.
method Analyzed a simple model-based approach and derived PAC sample complexity bounds.
result Established tight sample complexity bounds for value and policy learning.
We study a security threat to batch reinforcement learning and control where the attacker aims to poison the learned policy. The victim is a reinforcement learner / controller which first estimates the dynamics and the rewards from a batch data set, and then solves for the optimal policy with respect to the estimates. …
Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization. Towards the sample-efficient RL, we propose ranking policy gradient (RPG), a policy …
New approach to understand recurrent policies as FSMs without minimization.
problem Minimization of FSMs obscures the semantics of policy decisions.
method Start with unminimized FSM, apply interpretable reductions, use attention tool.
result Reveals insights into policy decisions not previously noticed.
End-to-end policy learning method improves CATE estimation.
problem Learning optimal treatment policies from partially observed data.
method Modified causal forest for policy learning.
result Maximizing policy value is equivalent to minimizing CATE.
Study online control of unknown time-varying systems with negative and positive results.
problem Online control of time-varying systems with unknown dynamics.
method Algorithmic upper bounds and lower bounds for different policy classes.
result Sublinear adaptive regret bounds for Disturbance Response policies.
Unified framework for understanding GRPO as U-statistic.
problem Theoretical properties of GRPO remain less studied.
method Unified framework through classical U-statistics.
result GRPO is asymptotically equivalent to an oracle policy gradient algorithm.
We study the problem of policy evaluation and learning from batched contextual bandit data when treatments are continuous, going beyond previous work on discrete treatments. Previous work for discrete treatment/action spaces focuses on inverse probability weighting (IPW) and doubly robust (DR) methods that use a reject…
The ability to discover approximately optimal policies in domains with sparse rewards is crucial to applying reinforcement learning (RL) in many real-world scenarios. Approaches such as neural density models and continuous exploration (e.g., Go-Explore) have been proposed to maintain the high exploration rate necessary…
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.
Develops optimal decision-making framework for uncertain counterfactuals.
problem Ensuring reliability of predictions in high-stakes decisions.
method Policy-Coupled Risk-Averse Conformal Prediction (PC-RACP).
result Optimal prediction sets for counterfactual decisions with valid coverage.
We consider the applications of the Frank-Wolfe (FW) algorithm for Apprenticeship Learning (AL). In this setting, we are given a Markov Decision Process (MDP) without an explicit reward function. Instead, we observe an expert that acts according to some policy, and the goal is to find a policy whose feature expectation…
We develop asymptotically optimal policies for the multi armed bandit (MAB), problem, under a cost constraint. This model is applicable in situations where each sample (or activation) from a population (bandit) incurs a known bandit dependent cost. Successive samples from each population are iid random variables with u…
Deep learning solves dynamic programming with recursive utility.
problem Challenges in solving high-dimensional discrete-time dynamic programming problems with recursive utility.
method Certainty Equivalent Learning (CEL) algorithm that learns certainty-equivalent value directly with neural networks.
result Accurate value and policy approximations in high-dimensional problems, comparable to VFI in some cases.
Study improves sampling efficiency of diffusion models using RL and PDEs.
problem Training neural stochastic differential equations without access to target samples.
method Proves equivalences between RL methods and PDEs, uses coarse time discretization.
result Improves sample efficiency and reduces computational cost.
We present a new approach to the problems of evaluating and learning personalized decision policies from observational data of past contexts, decisions, and outcomes. Only the outcome of the enacted decision is available and the historical policy is unknown. These problems arise in personalized medicine using electroni…
Reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. In this paper, we classify RL into direct and indirect RL according to how they seek the optimal policy of the Markov decision process problem. The former solves the optimal poli…
Study optimal policies under budget and coverage constraints.
problem Optimal policy learning with budget and coverage constraints.
method Combination of knapsack structure, affine threshold rule, linear programming relaxation, Greedy-Lagrangian (GLC), and rank-and-cut (RC) algorithms.
result GLC closely approximates the optimal solution and achieves near-optimal performance in finite samples; RC is approximately optimal under certain conditions.
Paper derives Thiele's equation for unit-linked policies in a stochastic volatility model.
problem Deriving pricing formula for unit-linked policies in a stochastic volatility model.
method Derives Thiele's differential equation for a unit-linked policy in the Heston-Hawkes model.
result Established a method to compute reserves in life insurance via solving Thiele's equation.
New policy optimizes risk and optimality in stochastic bandits.
problem Optimizing risk in stochastic bandits with heavy-tailed risk.
method Designing policies with worst-case optimality for expected regret and light-tailed risk distribution.
result Achieves worst-case optimality for expected regret and light-tailed risk distribution.
Paper bridges VI and GFlowNets, showing their equivalence in certain cases.
problem Modeling distributions over continuous and discrete structures.
method Demonstrates equivalence between VI and GFlowNets in specific scenarios.
result GFlowNets are more suitable for off-policy training without high gradient variance.
Develops a reinforcement learning algorithm for learning deterministic equilibrium policies in time-inconsistent control problems.
problem Learning equilibrium policies in time-inconsistent control problems.
method Continuous-time model-free reinforcement learning algorithm using deterministic policy gradient approach.
result Learned equilibrium policies in general time-inconsistent control problems.
In this paper, we point out a fundamental property of the objective in reinforcement learning, with which we can reformulate the policy gradient objective into a perceptron-like loss function, removing the need to distinguish between on and off policy training. Namely, we posit that it is sufficient to only update a po…
We consider a model in which a trader aims to maximize expected risk-adjusted profit while trading a single security. In our model, each price change is a linear combination of observed factors, impact resulting from the trader's current and prior activity, and unpredictable random effects. The trader must learn coeffi…
Paper tackles robust optimization under uncertainty using nested distance.
problem Optimizing under distributionally robust uncertainty with nested distance.
method Equivalent recursive and dynamic programming reformulations for tractable optimization.
result Optimal robust policies can be found efficiently using convex optimization.
Overview of risk-sensitive Markov decision processes with Optimized Certainty Equivalent.
problem Optimizing decision-making under risk in Markov processes.
method Analyzes risk-sensitive criteria using Optimized Certainty Equivalent, including entropic risk and Conditional Value-at-Risk.
result Conditions for the existence of optimal policies and solution procedures are provided.