New algorithm achieves optimal regret in average reward MDPs without prior bias information.
problem Achieving optimal regret in average reward MDPs with computational efficiency and without prior bias information.
method Projective Mitigated Extended Value Iteration (PMEVI) to compute bias-constrained optimal policies efficiently.
result First tractable algorithm with minimax optimal regret of O ~ ( s p ( h ∗ ) S A T ) \widetilde{\mathrm{O}}(\sqrt{\mathrm{sp}(h^*) S A T}) O ( sp ( h ∗ ) S A T ) . New algorithm reduces sample complexity for constrained MDPs.
problem Learning policies in constrained average-reward MDPs.
method Model-based algorithm for relaxed and strict feasibility settings.
result Achieves minimax-optimal bounds for constrained MDPs.
New method optimizes policies without assuming known link functions between preferences and rewards.
problem Policy alignment with unknown and unrestricted link functions.
method Formulates an f f f -divergence-constrained reward maximization problem, learning policies directly. result Induces a semiparametric single-index binary choice model for policy alignment.
Study improves unbiased recommender learning by addressing missing-reward bias.
problem Data bias caused by missing-reward observations in recommender systems.
method Proposes a novel estimator using propensity scores to mitigate both position and reward bias.
result The proposed estimator outperforms other methods, even with increased reward observation bias.
VaR-CPO optimizes VaR-constrained RL problems with conservative policy updates.
problem Optimizing VaR-constrained reinforcement learning problems.
method Combines Cantelli's inequality and trust-region framework for efficient and conservative optimization.
result Achieves zero constraint violations during training in feasible environments.
Novel methods generate diverse policies in reinforcement learning.
problem Generating diverse policies in reinforcement learning.
method Constrained optimization perspective, introducing new metrics, and novel policy generation methods.
result Improved novelty and performance of generated policies.
FOCOPS optimizes agent's behavior while adhering to constraints.
problem Optimizing agent's behavior while respecting safety constraints.
method FOCOPS solves a constrained optimization problem in policy space, then projects the solution back into the parametric space.
result FOCOPS achieves better performance on constrained robotics tasks.
Paper reduces variance in infinite horizon off-policy evaluation with bias reduction.
problem High variance in infinite horizon off-policy evaluation.
method Doubly robust augmentation of Liu et al. (2018a) method using learned value function.
result Significant reduction in bias with higher accuracy when either density ratio or value function is accurate.
KL-constrained API shows optimization issues and improved with regularization.
problem Optimization issues in KL-constrained API algorithms.
method Comparison of KL divergence as a constraint vs. regularizer, empirical evaluation.
result KL-constrained API is not guaranteed to converge and incurs linear regret.
PESCAL uses mediators to learn from confounded offline data.
problem Learning from confounded observational data in reinforcement learning.
method PESCAL uses mediator variables and the pessimistic principle to address confounding bias and distributional shift.
result It is sufficient to learn a lower bound of the mediator distribution function to mitigate distributional shift.
We find the optimal error for a constrained regression model under a linear model.
problem Minimizing error while adhering to demographic parity constraints.
method Proposed a minimax optimal error analysis for a demographic parity-constrained regression problem within a linear model.
result The minimax optimal error is characterized by $Θ( rac{dM}{n})$ .
A new algorithm CAP learns optimal policies from observational data with confounding bias and missing observations.
problem Offline contextual bandit with confounding bias and missing observations.
method CAP policy learning, forming reward function as solution of integral equation system, building confidence set, and greedily taking action with pessimism.
result Developed an upper bound to the suboptimality of CAP for the offline contextual bandit problem.
The paper optimizes policies constrained to Schur stabilizing controllers using a Newton-type algorithm.
problem Optimizing policies under linear constraints in control systems.
method Newton-type algorithm on a manifold of Schur stabilizing controllers with a Riemannian metric.
result Local convergence guarantees for the Newton-type algorithm without relying on exponential mapping or retractions.
Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While constraints may solve this issue, there is no closed form solution for general co…
New methods improve off-policy evaluation for survival outcomes with censoring.
problem Systematic underestimation of policy performance due to censoring bias in survival outcomes.
method Proposes IPCW-IPS and IPCW-DR to handle censoring bias in survival outcomes.
result The proposed methods are unbiased and achieve double robustness.
Oracle-efficient algorithm for offline RL with partial data coverage.
problem Offline reinforcement learning with partial data coverage and constraints.
method PDOCRL, a primal-dual algorithm with decomposed linear-programming formulation.
result Near-optimal, near-feasible policy with \(\widetilde{\mathcal O}(ε^{-2})\) sample guarantee.
A new approach combines prior knowledge with learning to adapt quickly to new tasks.
problem Adapting quickly to new tasks using prior knowledge.
method Combines behavior prior, robust off-policy learning, and value function representation.
result Achieves competitive adaptation performance compared to meta reinforcement learning baselines.
A new Q-learning variant reduces underestimation bias in deep reinforcement learning.
problem Underestimation bias in deep reinforcement learning policies.
method Introducing a novel, parameter-free Deep Q-learning variant.
result Significantly outperforms existing approaches and improves state-of-the-art performance.
ConQUR tackles delusional bias in deep Q-learning, improving performance in Atari games.
problem Delusional bias in deep Q-learning.
method Efficient methods to mitigate delusional bias by training Q-approximators with consistent labels and a search framework.
result Improves performance in Atari games, sometimes dramatically.
Offline RL tackles resource-constrained online deployment with improved policy transfer.
problem Training policies with limited online features using a rich offline dataset.
method Introduce a policy transfer algorithm that first trains a teacher agent with full offline features and then transfers knowledge to a student agent with limited online features.
result Consistent improvement in performance over baseline methods on resource-constrained datasets.
This paper merges deterministic policy gradient estimations to improve deep reinforcement learning performance.
problem The bias-variance tradeoff in estimating and using policy gradients for deep reinforcement learning.
method Introduces elite policy gradients and a two-step merging method to balance bias-variance tradeoffs.
result Two-step merging outperforms interpolation merging and state-of-the-art algorithms on benchmark control tasks.
Proposes a method to learn policies from offline data with reduced bias.
problem Learning policies from offline data with reduced bias and complexity constraints.
method Cross-fitted debiasing device for policy learning from offline data.
result Achieves N \sqrt N N regret for complex policy classes with a product-of-errors nuisance remainder. DML-IV improves IV regression for learning decision policies by reducing bias.
problem Spurious correlations in offline datasets caused by hidden confounders.
method Double/debiased machine learning (DML) framework to reduce bias in two-stage IV regression.
result DML-IV outperforms state-of-the-art methods and learns high-performing policies.
Framework improves policy generalizability under biased training data.
problem Learning policies that generalize to a target population from biased training data.
method Characterizes sample selection bias using a selection variable, optimizes minimax value over uncertainty set, derives efficient algorithm.
result Policies generalize to target population, outperform standard methods.
This work overcomes bias in concave multi-objective reinforcement learning.
problem Gradient bias in policy gradient methods for concave scalarized multi-objective reinforcement learning.
method Developed a Natural Policy Gradient (NPG) algorithm with a multi-level Monte Carlo (MLMC) estimator.
result Achieved optimal O ~ ( ε − 2 ) \widetilde{\mathcal{O}}(ε^{-2}) O ( ε − 2 ) sample complexity for computing an ε ε ε -optimal policy. New estimator reduces bias-variance tradeoff in Markovian interference experiments.
problem Estimating impact of interventions in systems with limited resources.
method Differences-In-Q (DQ) estimator for on-policy policy evaluation.
result DQ estimator has exponentially smaller variance than off-policy methods.
Canary optimizes VaR-constrained RL problems with a conservative bound using Cantelli's inequality.
problem Optimizing reinforcement learning policies under VaR constraints in dense cost regimes.
method Employing Cantelli's inequality to create a conservative and smooth bound on VaR constraints based on moments of cost returns. Extending trust-region framework for worst-case bounds on policy improvement and constraint violation.
result Canary reliably satisfies VaR constraints with fewest violations and earliest permanent satisfaction, while maintaining reward competitiveness.
Paper proposes a bias-constrained deep learning approach to non-linear estimation.
problem Designing unbiased estimators for non-linear models.
method Bias Constrained Estimator (BCE) using deep learning with bias constraints.
result Asymptotic MVUEs with Cramer Rao bound performance.
VRER selectively reuses past observations to reduce variance in policy optimization.
problem Lack of effective experience replay for accelerating policy optimization in complex systems.
method Variance Reduction Experience Replay (VRER) framework that selectively reuses informative samples.
result VRER reduces gradient variance and improves policy learning over state-of-the-art algorithms.
In importance sampling (IS)-based reinforcement learning algorithms such as Proximal Policy Optimization (PPO), IS weights are typically clipped to avoid large variance in learning. However, policy update from clipped statistics induces large bias in tasks with high action dimensions, and bias from clipping makes it di…
Machine learning models predict brain age with systematic bias, corrected in this study.
problem Systematic bias in machine learning regression models for brain age prediction.
method General constrained optimization approach to correct bias.
result Our method effectively eliminates the bias from brain age predictions.
Automates bias control in reinforcement learning algorithms.
problem Overestimation bias in reinforcement learning algorithms.
method Data-driven approach for automatic selection of bias control hyperparameters.
result Significant reduction in the number of interactions while maintaining performance.
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.
PDCA algorithm learns policies for RL with constraints using a primal-dual approach.
problem Offline constrained reinforcement learning with general function approximation.
method Primal-Dual-Critic Algorithm (PDCA) using a primal-dual approach.
result PDCA finds a near saddle point of the Lagrangian, nearly optimal for constrained RL.
New model reduces matrix factorization bias, yielding truly low-rank solutions.
problem Gradient descent's implicit bias in matrix factorization.
method Introducing a new factorization model with constrained factors and diagonal components.
result The new model consistently exhibits a strong implicit bias, yielding truly low-rank solutions.
BRPO optimizes batch RL policies to better exploit state-action differences.
problem Batch RL's conservatism limits exploitation of state-action differences.
method Proposes residual policies and derives BRPO to maximize policy performance.
result BRPO achieves state-of-the-art performance in various tasks.
A new estimator reduces bias and variance in ranking policy evaluation.
problem Estimating ranking policies using logged data in recommender systems.
method Cascade Doubly Robust estimator based on the cascade assumption.
result The estimator reduces bias and variance compared to existing methods.
Paper proposes risk-averse reinforcement learning algorithms.
problem Managing model uncertainty in reinforcement learning.
method Entropic risk constrained policy gradient and actor-critic algorithms.
result Demonstrates usefulness of risk-averse algorithms on various domains.
We propose a policy improvement algorithm for Reinforcement Learning (RL) which is called Rerouted Behavior Improvement (RBI). RBI is designed to take into account the evaluation errors of the Q-function. Such errors are common in RL when learning the Q Q Q -value from finite past experience data. Greedy policies or even …
Paper tackles overestimation bias in continuous control, improving performance by 25%.
problem Overestimation bias in off-policy learning.
method Truncated Quantile Critics (TQC) combines distributional representation, truncation, and ensembling of critics.
result TQC outperforms state-of-the-art methods by 25% on the Humanoid environment.
This work compares regularization and constrained inference for label constraints in machine learning.
problem Improving model performance with label constraints in machine learning.
method Comparison of regularization and constrained inference strategies.
result Constrained inference reduces population risk by correcting model violations, while regularization narrows the generalization gap but introduces bias.
For an autonomous agent, executing a poor policy may be costly or even dangerous. For such agents, it is desirable to determine confidence interval lower bounds on the performance of any given policy without executing said policy. Current methods for exact high confidence off-policy evaluation that use importance sampl…
Algorithm optimizes constrained reinforcement learning with dual variables.
problem Minimizing convex functional subject to convex constraint in large state spaces.
method VPDPO algorithm using Lagrangian and Fenchel duality.
result Achieves sublinear regret and constraint violation, globally optimal policy.
DOLCE improves off-policy evaluation and learning by decomposing effects.
problem Bias in off-policy evaluation and learning due to policy mismatch.
method Uses lagged contexts and a moment-based training procedure to decompose and cancel bias.
result DOLCE achieves substantial improvements in off-policy evaluation and learning.
QFIL improves offline RL by filtering data to reduce bias and variance.
problem Improving offline reinforcement learning policies with limited data.
method QFIL uses a filtered dataset to improve policies, trading off bias and variance through quantile selection.
result QFIL provides a safe policy improvement step with function approximation and effectively balances bias and variance.
FFN addresses spectral bias in neural value approximation, improving reinforcement learning performance.
problem Spectral bias in neural value approximation, leading to slow convergence and poor performance.
method Proposes Fourier feature networks (FFN) to overcome spectral bias by using a composite neural tangent kernel.
result FFN achieves state-of-the-art performance on challenging continuous control domains with faster convergence and better stability.
We consider the core reinforcement-learning problem of on-policy value function approximation from a batch of trajectory data, and focus on various issues of Temporal Difference (TD) learning and Monte Carlo (MC) policy evaluation. The two methods are known to achieve complementary bias-variance trade-off properties, w…
KCRL learns stable policies for nonlinear systems with formal guarantees.
problem Lack of stabilization guarantees in RL methods for safety-critical systems.
method KCRL uses Krasovskii's Lyapunov functions as a stability constraint and a primal-dual approach to learn stabilizing policies.
result KCRL guarantees learning a stabilizing policy in a finite number of interactions.