Generative neural nets learn deep policies conditioned on goals.
problem Learning optimal policies for specific goals in reinforcement learning.
method Goal-conditioned neural nets that generate deep neural policies.
result Single learned policy generator can achieve any desired return.
This paper investigates how policy conditioning affects reinforcement learning stability.
problem Improving stability and generalization of reinforcement learning agents.
method The authors study Jacobian conditioning behavior during policy optimization and propose a conditioning regularization algorithm.
result The proposed conditioning regularization algorithm enhances reinforcement learning agent generalization.
Success conditioning optimizes policies by imitating successful trajectories, solving a trust-region optimization problem.
problem Improving policies through random actions that lead to desired outcomes.
method Success conditioning, which involves collecting and updating policies based on successful trajectories.
result Success conditioning solves a trust-region optimization problem, maximizing policy improvement with a χ2 divergence constraint. A novel approach learns goal-conditioned policies for locomotion using batch RL.
problem Training goal-conditioned policies for rotation invariant locomotion.
method Data augmentation and Siamese framework for invariance.
result Our approach outperforms existing RL algorithms on 3D locomotion agents.
The paper introduces a new framework for off-policy reinforcement learning.
problem Improving off-policy reinforcement learning algorithms.
method Conceptual framework based on conditional importance sampling.
result Theoretical analysis and concrete algorithm investigation.
This work analyzes the gap between off-policy and on-policy policy gradient methods and provides conditions to reduce this gap.
problem The gap between off-policy and on-policy policy gradient methods and conditions to reduce it.
method Theoretical analysis and empirical evidence of conditions to reduce the on-off gap.
result Conditions to reduce the on-off gap between off-policy and on-policy policy gradient methods.
We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of transition probabilities. We prove that such approximate corrections are sufficien…
This work ensures policy gradient methods converge to global optima for certain control problems.
problem Non-convex optimization challenges in policy gradient methods for complex control problems.
method Identifies structural properties ensuring non-convex objective functions have no suboptimal stationary points.
result Policy gradient methods converge to global optima under certain conditions, satisfying a Polyak-Lojasiewicz condition.
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.
A new method learns policies from sub-optimal trajectories.
problem Reinforcement learning's brittleness and difficulty in tuning.
method Conditioning policies on the reward of sub-optimal trajectories.
result Effective policies can be learned without expert demonstrations.
New RL algorithms learn policies competitive with best in class without assuming optimal policy.
problem Agnostic RL where best policy not necessarily optimal.
method First-order optimization in non-Euclidean space, reducing to policy learning.
result Sample complexity upper bounds for three algorithms under VGD condition.
Large deviations theory applied to policy gradient methods.
problem Understanding convergence of policy gradient methods in reinforcement learning.
method Large deviation rate function and contraction principle from large deviations theory.
result Convergence properties of policy gradient methods can be extended to various policy parametrizations.
New framework estimates treatment effects based on preferences.
problem Estimating treatment effects with flexible outcomes.
method Preference-based Conditional Treatment Effect (CPTE) framework.
result CPTE provides interpretable targets and new identifiability conditions.
Improved RCPs for MABs using normalized weight functions.
problem Slow convergence and inferior rewards in RCPs for MABs.
method Generalized marginalization of rewards using normalized weight functions.
result Improved RCPs become competitive with classic methods.
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.
Bayesian approach for policy search in stochastic domains.
problem Policy search in stochastic domains.
method Nested probabilistic programs, Lightweight Metropolis-Hastings (LMH) adaptation.
result Similar quality policies learned with simpler algorithm.
This paper bridges the gap between theoretical and practical OPE for bandit problems.
problem Estimating the value of a target policy from samples generated by different policies.
method Categorizing OPE situations based on evaluation policy properties, proposing a meta-algorithm.
result Meta-algorithm successfully bridges the gap between theoretical and practical OPE for bandit problems.
Cramming method evaluates learned policies from contextual bandits efficiently.
problem Evaluating final learned policies from contextual bandit algorithms.
method On-policy evaluation using a single pass of data, ensuring consistency and asymptotic normality.
result Cramming method reduces evaluation standard error by approximately 40% compared to off-policy methods.
Generative Adversarial Regression (GAR) learns risk scenarios robustly across policies.
problem Learning risk scenarios for conditional risk objectives.
method Generative adversarial framework for risk matching.
result GAR produces more stable and risk-preserving scenarios than baselines.
Study policy gradient and actor-critic methods for continuous-time reinforcement learning.
problem Continuous-time reinforcement learning with policy gradient and actor-critic approaches.
method Regularized exploratory formulation, martingale approach, simultaneous policy and value function updates.
result Proposed two types of actor-critic algorithms for online and offline learning.
New offline RL study shows exponential sample requirement for accurate policy evaluation.
problem Understanding statistical limits of offline RL with linear function approximation.
method Analyzes necessary representational and distributional conditions for sample-efficient offline reinforcement learning.
result Even with realizability and good feature coverage, offline RL requires exponential samples for accurate policy evaluation.
A new policy learning method allows policies to abstain when uncertain, improving safety and applicability.
problem Risk of making decisions without full confidence in uncertain predictions.
method Policy learning with abstention, identifying near-optimal policies and constructing an abstention rule.
result Improved safety and applicability in policy learning, with theoretical guarantees.
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.
New framework for PMD convergence in non-tabular environments.
problem Applying PMD to general policy classes with weak closure conditions.
method Develops a theoretical framework with a novel smoothness notion.
result Obtains upper bounds on convergence rate for non-tabular environments.
Work establishes conditions for bias-free policy optimization.
problem Improving policy optimization methods without introducing bias.
method Established conditions for parametric critic without bias.
result Identified bias in current policy optimization algorithms.
Paper develops NPG for risk-averse RL with ECRMs, proving global convergence.
problem Ensuring reliable performance in stochastic RL problems with risk-averse policies.
method Developed natural policy gradient updates for ECRMs-based RL problems, proving global optimality and iteration complexity.
result Global convergence of risk-averse NPG algorithm with ECRMs.
Method solves long-horizon robotic tasks via imitation and reinforcement learning.
problem Long-horizon robotic tasks with complex sequences of actions.
method Two-phase approach: imitation learning followed by reinforcement learning.
result Method can scale to challenging long-horizon tasks.
A new method removes policy optimization in adversarial imitation learning.
problem Adversarial imitation learning's delicate alternated optimization.
method Explicitly condition discriminator on two policies, solving generator's optimization problem directly.
result Simpler approach competitive to prevalent methods.
This study shows how trade policy uncertainty affects stock-T bill correlations.
problem The impact of trade policy uncertainty on stock-T bill relationships.
method Extended Dynamic Conditional Correlation (DCC) framework incorporating exogenous variables.
result Trade policy uncertainty significantly alters stock-T bill correlations, especially under specific political conditions.
This work uses statistical bootstrapping to provide accurate confidence intervals for policy value in reinforcement learning.
problem Bias in estimating policy value using empirical transitions and rewards.
method Statistical bootstrapping to produce calibrated confidence intervals for the true policy value.
result Statistical bootstrapping can yield correct confidence intervals under certain conditions, and mechanisms are proposed to mitigate these conditions.
Boosting for off-policy learning reduces empirical risk.
problem Learning from logged bandit feedback without labeled data.
method A boosting algorithm optimizing policy's expected reward.
result Excess empirical risk decreases with each round of boosting.
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…
Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to the actor involves a log-likelihood update weighted by the action-values, with the addition of entropy regularization for soft variants. In th…
We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term. The extant entropy-regularized MDPs can be cast into our framework. Moreover, under our framework, …
This work characterizes conditions for offline policy evaluation in reinforcement learning.
problem Understanding when classical methods succeed in offline policy evaluation for linear function approximation.
method Control-theoretic and linear-algebraic conditions for classical methods (FQI and LSTD).
result A precise hierarchy of regimes under which these estimators succeed, and a complete picture of their behavior.
Quantum algorithms speed up reinforcement learning policies in large state-action spaces.
problem Limitations of quantum access in training reinforcement learning policies.
method Designing quantum algorithms to train reinforcement learning policies.
result Quantum algorithms offer full quadratic speed-ups in sample complexity for well-behaved policies.
As all physical adaptive quantum-enhanced metrology schemes operate under noisy conditions with only partially understood noise characteristics, so a practical control policy must be robust even for unknown noise. We aim to devise a test to evaluate the robustness of AQEM policies and assess the resource used by the po…
New insights into RL with weak function approximation.
problem Statistical complexity of RL with function approximation in large state spaces.
method Agnostic policy learning framework, exploring environment access, coverage, and representational conditions.
result Characterization of fundamental performance bounds and statistical separations.
Sharp policy value estimation for contextual bandits with unobserved confounders.
problem Estimating policy value under unobserved confounders with sensitivity analysis.
method Kernel method to approximate conditional moment constraints, leveraging f-divergence.
result Sharp lower bound of policy value, avoiding coarse relaxation of uncertainty set.
Analyzes securitization impacts on monetary and fiscal policies.
problem Impact of securitization on monetary and fiscal policies.
method Develops optimal conditions, identifies constraints, introduces new decision models.
result Identifies constraints and interactions of securitization with capital-reserve requirements.
This paper proposes a method to evaluate policies using quantile metrics, improving upon existing mean-based approaches.
problem Evaluating policies using mean-based metrics ignores the variability of outcomes, especially in skewed reward distributions.
method The paper introduces a doubly-robust inference procedure for quantile off-policy evaluation using deep conditional generative learning.
result The proposed estimator outperforms classical OPE estimators for mean outcomes in heavy-tailed reward distributions.
VPP learns joint policies for multi-agent RL through interactions.
problem Learning effective joint policies for multi-agent reinforcement learning.
method VPP integrates variational inference into policy layers for efficient sampling and differentiability.
result VPP outperforms previous methods on large-scale multi-agent tasks.
This paper tackles robust policy learning under concept drifts, improving upon existing methods.
problem Tackles robust policy learning under concept drifts, improving upon existing methods.
method Develops a doubly-robust estimator and a learning algorithm to maximize policy value within a given policy class.
result The proposed algorithm achieves sub-optimality gap of the order κ(Π)n−1/2, demonstrating substantial improvement over existing benchmarks. The paper proposes a new policy for optimal treatment allocation based on quantile treatment effects.
problem Optimal treatment allocation policies that target distributional welfare, especially when individuals are heterogeneous.
method The approach involves allocating treatments based on the conditional quantile of individual treatment effects (QoTE), considering both prudent and negligent policymakers.
result The proposed minimax policies are robust to model uncertainty and can be generalized to various settings.
Paper tackles efficient evaluation of natural stochastic policies in offline RL.
problem Efficiency issues in evaluating natural stochastic policies due to unknown evaluation policy.
method Derive efficiency bounds for tilting and modified treatment policies, propose nonparametric estimators.
result Proposed estimators attain efficiency bounds under lax conditions and enjoy partial double robustness.
Paper introduces CageBO for optimizing complex public policy problems.
problem Complex decision-making and implicit constraints in public policy.
method CageBO framework using conditional variational autoencoder.
result CageBO outperforms baselines in optimizing large-scale police redistricting.
The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free RL approach directly learns the policy based on data samples. Although using many samples tends to improve the accuracy of policy learning, c…
New IS methods fail to reduce variance in long-horizon MDPs.
problem High variance in off-policy evaluation for long-horizon domains.
method Conditional Monte Carlo analysis of IS methods.
result No strict variance reduction for per-decision or stationary IS methods in finite horizon MDPs.