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. 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.
New RL method reduces sample complexity for large policy spaces.
problem Large-scale RL with unknown optimal policies and state/action spaces.
method Introduces eluder dimension for policy space, proving near-optimal sample complexity.
result Near-optimal sample complexity upper bound that depends linearly on eluder dimension.
The paper analyzes the sample complexities for policy evaluation with linear function approximation.
problem Policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes.
method Investigates sample complexities for two policy evaluation algorithms: TD and TDC.
result Establishes high-probability sample complexity bounds for policy evaluation algorithms.
This work explores representation complexity in RL paradigms, revealing model-based RL as the easiest task.
problem Investigating the representation complexity gap among model-based, policy-based, and value-based RL.
method Demonstrated through analysis of Markov decision processes (MDPs) and introduced new classes of MDPs.
result Representation complexity hierarchy: model-based RL > policy-based RL > value-based RL.
Adaptive exploration scheme for evaluating multiple policies with different rewards.
problem Online multi-reward multi-policy evaluation.
method Adapted ( ε , δ ) (ε,δ) ( ε , δ ) -PAC perspective and MR-NaS exploration scheme to minimize sample complexity. result Demonstrated effectiveness of adaptive exploration in tabular domains.
A new imitation learning method uses random search for simple policies, outperforming complex models.
problem Complexity and reward dependency issues in imitation learning.
method Derivative-free optimization with simple linear policies and random search.
result The proposed method achieves competitive performance on MuJoCo locomotion tasks without a direct reward signal.
Backward exploration reduces sample complexity in policy evaluation.
problem Empirical policy evaluation in reinforcement learning.
method Backward exploration algorithms from high-cost states.
result Reduced average-case sample complexity to O ( log S ) O(\log S) O ( log S ) . New method QMLE performs well in complex action spaces without policy gradients.
problem Why policy gradients outperform action-value methods in complex action spaces.
method QMLE framework for action-value methods based on three principles.
result QMLE performs comparably to policy gradient methods in complex action spaces.
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.
New offline RL method handles average-reward MDPs with single-policy coverage.
problem Challenges in offline reinforcement learning due to distribution shift and non-uniform coverage.
method Develops an algorithm based on pessimistic discounted value iteration with quantile clipping.
result First fully single-policy sample complexity bound for average-reward offline RL.
On-policy reinforcement learning (RL) algorithms have high sample complexity while off-policy algorithms are difficult to tune. Merging the two holds the promise to develop efficient algorithms that generalize across diverse environments. It is however challenging in practice to find suitable hyper-parameters that gove…
Proposes log density gradient to improve reinforcement learning sample complexity.
problem Residual error in gradient estimation in policy gradient methods.
method Log density gradient method to correct residual error, using state-action discounted distributional formulation.
result Min-max optimization method to approximate log density gradient with on-policy samples, achieving sample complexity of m − 1 / 2 m^{-1/2} m − 1/2 . This paper bridges offline and online RL by studying policy finetuning with a reference policy.
problem Sample-efficient reinforcement learning in online and offline settings.
method Design of policy finetuning algorithms and analysis of sample complexity.
result Theoretical analysis shows that the optimal policy finetuning algorithm is either offline reduction or purely online RL.
DSPI connects natural policy gradient to policy iteration, proving global convergence.
problem Optimizing policies in reinforcement learning.
method DSPI framework, combining smoothed policy iteration and natural policy gradient.
result DSPI achieves geometric convergence and optimal complexity for policy optimization.
Paper achieves ε − 2 ε^{-2} ε − 2 sample complexity for actor-critic methods with minimal assumptions.
problem Achieving ε − 2 ε^{-2} ε − 2 sample complexity for actor-critic methods under minimal assumptions. method Single-loop, single-timescale implementation; coupled Lyapunov drift framework.
result First i l d e O ( ε − 2 ) ilde{\mathcal{O}}(ε^{-2}) i l d e O ( ε − 2 ) sample complexity guarantee for finding an ε ε ε -optimal policy. Optimistic actor-critic tackles linear MDPs with parametric policies.
problem Theoretical limitations of existing actor-critic methods for linear MDPs.
method Proposes an optimistic actor-critic framework with parametric log-linear policies and approximate Thompson sampling.
result Achieves state-of-the-art sample complexity in both on-policy and off-policy settings.
New analysis improves sample complexity for vanilla policy gradient methods.
problem Improving sample complexity guarantees for vanilla policy gradient methods.
method Adapting tools from SGD analysis to policy gradient methods, with smoothness and gradient approximation assumptions.
result Established improved sample complexity bounds for convergence and global optimum.
Study shows sample complexity for learning optimal policies in SSP with generative model.
problem Learning optimal policies in Stochastic Shortest Path problems.
method Derive and prove lower and upper bounds on sample complexity.
result Lower bound of Ω ( S A B ⋆ 3 / ( c min ε 2 ) ) Ω(SAB_{\star}^3/(c_{\min}ε^2)) Ω ( S A B ⋆ 3 / ( c m i n ε 2 )) samples for general case, and up to logarithmic factors for bounded hitting time condition. Bayesian optimization improves policy search in reinforcement learning.
problem Finding optimal policies with high variance estimates from random samples.
method Develops an algorithm combining Bayesian optimization and policy gradients.
result Improves sample complexity and reduces variance in empirical evaluations.
Reduces policy space complexity for reinforcement learning.
problem Efficiency in exploring vast policy spaces in reinforcement learning.
method Uses Rényi divergence and l 1 l_1 l 1 norm to determine sample size for accurate policy approximation. result Established error bounds for sample size requirements in model-based and model-free settings.
We propose to improve trust region policy search with normalizing flows policy. We illustrate that when the trust region is constructed by KL divergence constraints, normalizing flows policy generates samples far from the 'center' of the previous policy iterate, which potentially enables better exploration and helps av…
NPMD uses CNNs to optimize policies on low-dimensional manifolds, reducing sample complexity.
problem Explaining the effectiveness of deep policy gradient methods in high-dimensional RL.
method Neural policy mirror descent (NPMD) with CNNs, considering state spaces as low-dimensional manifolds.
result NPMD finds ε-optimal policies with O(ε^(-d/α-2)) samples, leveraging low-dimensional structure.
CPR models complex decision processes by breaking them into context-specific policies, improving interpretability and accuracy.
problem Interpreting dynamic human decision-making processes in medical contexts.
method Develops Contextualized Policy Recovery (CPR) framework for multi-task learning, modeling each context-specific policy as a linear map.
result Achieves state-of-the-art performance in predicting medical decisions, closing the gap between interpretable and black-box methods.
New RL algorithm learns robust policies without knowing nominal model.
problem Designing robust policies for RL with unknown nominal model.
method Model-based RL algorithm with three uncertainty set forms.
result Precise sample complexity for each uncertainty set.
New reinforcement learning algorithm achieves instance-optimal sample complexity.
problem Achieving low regret and identifying optimal policies in reinforcement learning.
method A novel planning-based algorithm that explicitly accounts for state visitation distributions.
result The proposed algorithm attains nearly minimax optimal sample complexity, improving over worst-case bounds.
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.
Study shows hard sample complexity for learning optimal policies in stochastic shortest path problems.
problem Learning optimal policies in stochastic shortest path problems.
method Analyzes sample complexity with and without generative models, derives lower and upper bounds.
result Proves sample complexity bounds and impossibility of horizon-free regret in SSPs.
Study nonparametric estimator for Markov chain transition matrices in offline setting.
problem Estimating transition matrices of finite controlled Markov chains from logged data.
method Developed sample complexity bounds and conditions for minimaxity.
result Achieving certain statistical risk requires balancing mixing properties and sample size.
AE-LSVI identifies near-optimal policies in complex systems with minimal data.
problem Identifying near-optimal policies in complex, costly data acquisition systems.
method Combines optimism and pessimism for active exploration in a generative model setting.
result Proves near-optimal policy identification over entire state spaces with polynomial sample complexity.
Improved API to achieve optimal error bound and query complexity in local planning.
problem Efficient local planning in discounted MDPs with linear approximation.
method Confident Approximate Policy Iteration (CAPI) for stationary policies, applying to local access simulators.
result Achieves optimal accuracy and query complexity bounds, improving over API.
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…
Paper analyzes NAC with neural networks for efficient policy optimization.
problem Improving sample and iteration complexity in policy optimization.
method Entropy regularization, averaging, neural network approximation, and optimization techniques.
result Entropy regularization and averaging ensure stability and sharp sample complexity bounds.
We study the sample complexity of approximate policy iteration (PI) for the Linear Quadratic Regulator (LQR), building on a recent line of work using LQR as a testbed to understand the limits of reinforcement learning (RL) algorithms on continuous control tasks. Our analysis quantifies the tension between policy improv…
Algorithm extsc{Pedel} learns near-optimal policies efficiently on specific problems.
problem Learning near-optimal policies in linear MDPs with minimal samples.
method Online experiment design to focus exploration on relevant directions.
result Achieves instance-dependent complexity, outperforming minimax-optimal algorithms.
New framework studies policy learning problems under data scarcity.
problem Learning improving policies when data is insufficient.
method Developed a mathematical framework for policy learning problems.
result Reduced policy learning problems to simpler ones in sample complexity.
DBQPG improves policy gradient estimation with fewer samples.
problem Accurate policy gradient estimation with limited samples.
method Deep Bayesian Quadrature Policy Gradient (DBQPG).
result DBQPG provides more accurate and less variable gradient estimates.
Paper analyzes sample complexity for offline f f f -divergence-regularized contextual bandits.
problem Lack of tight analyses for sample complexity in offline reinforcement learning.
method Novel pessimism-based analysis for reverse KL divergence, establishing i l d e O ( ε − 1 ) ilde{O}(ε^{-1}) i l d e O ( ε − 1 ) sample complexity. result Achieves i l d e O ( ε − 1 ) ilde{O}(ε^{-1}) i l d e O ( ε − 1 ) sample complexity for reverse KL divergence, surpassing existing bounds. VRER selectively reuses samples to improve policy optimization in complex systems.
problem Lack of effective reuse of historical samples in reinforcement learning.
method Variance reduction based experience replay (VRER) framework.
result VRER accelerates policy optimization and enhances performance.
Develops an anytime-valid framework for optimal policy identification from logged contextual bandit data.
problem Selecting the optimal policy from a candidate policy class while monitoring evidence continuously.
method Constructs a time-indexed set that retains the true optimal policy set uniformly over time.
result The procedure allows the analyst to monitor policy values, eliminate clearly suboptimal policies, and stop at data-dependent times without invalidating inference.
Simplifies complex RL policies by ranking important decisions.
problem Complexity in RL policies makes them hard to analyze and interpret.
method Statistical fault localisation to rank states and prune unimportant decisions.
result Pruned policies can perform similarly to original policies, improving interpretability.
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 algorithm reduces bias in off-policy reinforcement learning.
problem Challenges in designing off-policy reinforcement learning algorithms.
method Doubly robust off-policy actor-critic (DR-Off-PAC) with a single timescale structure.
result Establishes the first overall sample complexity analysis for a single time-scale off-policy AC algorithm.
Hierarchical decoupling improves sample efficiency for complex robots.
problem Learning long-range behaviors on complex robots.
method Two-part policy: low-level imitation and high-level transfer, with KL regularization.
result Hierarchical transfer significantly improves zero-shot high-level transfer and stabilizes learning.
Sharp analysis improves RLHF sample complexity with KL-regularization.
problem Improving RLHF sample complexity with KL-regularization.
method Sharp analysis of KL-regularized contextual bandits and RLHF.
result Achieved an O(1/ε) sample complexity when ε is sufficiently small.
Paper analyzes neural network complexity for planning problems.
problem Understanding neural network complexity for planning policies.
method Circuit complexity analysis for relational neural networks.
result Three classes of planning problems identified based on network complexity.
Transfer learning benefits vary in DRL, affecting representation and policy learning.
problem Understanding how much of DRL's sample complexity is due to representation learning.
method Transfer learning experiments comparing performance on related games.
result Benefits of transfer learning are highly variable and non-symmetric across tasks.
ZDPG learns model-free policies without critics, improving on PG.
problem Model-free policy learning in complex dynamic problems.
method Approximates policy-reward gradients via two-point stochastic evaluations of the Q-function.
result Restores true model-free policy learning without critics, with improved stability and efficiency.