Entropy-regularized NPG converges linearly with linear function approximation.
problem Analyzing convergence of entropy-regularized NPG with function approximation.
method Established finite-time convergence analyses with entropy regularization and linear function approximation.
result Entropy-regularized NPG achieves linear convergence up to a function approximation error.
Study on distributional TD learning with linear approximations for better return estimation.
problem Estimating the return distribution of a policy in reinforcement learning.
method Finite-sample analysis of distributional TD learning with linear function approximation, using the linear-categorical Bellman equation and exponential stability arguments for products of random matrices.
result Sample complexity of linear distributional TD learning matches that of classic linear TD learning, indicating similar difficulty in estimating return distribution versus its expectation.
New algorithms improve distributional TD learning with linear approximations.
problem Estimating return distributions in reinforcement learning.
method Fine-grained analysis of linear-categorical Bellman equation, variance reduction techniques.
result Tight sample complexity bounds for distributional TD learning with linear approximations.
Study approximates nonlinear functionals using deep ReLU networks.
problem Approximating nonlinear continuous functionals with neural networks.
method Constructs continuous piecewise linear interpolation under simple triangulation, analyzes rates of approximation.
result Established rates of approximation for functional deep ReLU networks.
Global approximation for piecewise linear paths via signatures.
problem Global approximation theorems for piecewise linear paths.
method Using signatures of piecewise linear paths and their density in L p L^p L p -norms. result Linear functionals of signatures are dense in L p L^p L p -norms under an integrability condition. Papers learn from data to make decisions without interacting, improving on previous methods.
problem Achieving optimal decision-making from offline data with non-linear function approximation.
method Pessimistic Nonlinear Least-Square Value Iteration (PNLSVI) with three innovative components.
result Achieves minimax optimal instance-dependent regret for non-linear function approximation.
UCRL2-VTR achieves nearly optimal regret for learning MDPs with linear function approximation.
problem Learning infinite-horizon average-reward MDPs with linear function approximation.
method UCRL2-VTR algorithm with Bernstein-type bonus.
result Achieves a regret of i l d e O ( d D T ) ilde{O}(d\sqrt{DT}) i l d e O ( d D T ) with matching lower bound. New methods stabilize Q-learning with linear approximations.
problem Stabilizing Q Q Q -learning with linear function approximation. method Target network and truncation.
result Provably stable Q Q Q -learning with linear function approximation. Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where function approximation must be deployed to approximate either the value function or the policy. The introduction of function approximation raises a fundamental set of challenges involving computational …
Logarithmic regret achieved in RL with linear function approximation.
problem Achieving logarithmic regret in reinforcement learning with linear function approximation.
method LSVI-UCB for linear MDP assumption, UCRL-VTR for linear mixture MDP assumption.
result Logarithmic regret bounds established for RL with linear function approximation.
Generalizes neural network approximation to infinite-dimensional manifolds and derivatives.
problem Approximating differentiable maps on infinite-dimensional manifolds.
method Proves a weighted Nachbin theorem to establish universal approximation for differentiable maps, including derivatives.
result Linear functions of the signature can approximate path space functionals including their derivatives.
Efficiently plans large MDPs with weak function approximations.
problem Planning in large MDPs with limited function approximation capabilities.
method Uses linear value function approximation with weak requirements and a generative oracle.
result Produces almost-optimal actions for any state with polynomial computation time.
Universal approximation theorem for differentiable maps on infinite-dimensional manifolds
problem Approximation of differentiable maps on infinite-dimensional manifolds
method Weighted universal approximation theorem
result Universal approximation theorem for differentiable maps
This paper concerns a method of selecting a subset of features for a sequential logit model. Tanaka and Nakagawa (2014) proposed a mixed integer quadratic optimization formulation for solving the problem based on a quadratic approximation of the logistic loss function. However, since there is a significant gap between …
New algorithm FLUTE achieves uniform-PAC convergence in RL with linear approx.
problem RL with linear function approximation lacks uniform-PAC guarantees.
method FLUTE algorithm with minimax value function estimator and multi-level partition scheme.
result Uniform-PAC convergence to optimal policy with high probability.
This work improves sample efficiency in neural function approximation for reinforcement learning.
problem Improving sample efficiency in reinforcement learning with neural function approximation.
method Study of function approximation with two-layer neural networks (ReLU and polynomial activations) under generative and realizability models.
result Significant improvement in sample complexity compared to linear methods.
Greedy method adds neurons one by one for better function approximation.
problem Function approximation in neural networks.
method Growing deep neural network by adding one neuron at a time with non-linear activation.
result Accurate approximants for model problems in function approximation.
ENIAC method optimizes and explores complex RL problems with non-linear policies.
problem Theoretical understanding of non-linear policies in RL with strategic exploration.
method ENIAC, an actor-critic method for non-linear function approximation.
result ENIAC finds near-optimal policies in polynomial exploration rounds under bounded eluder dimension.
Q Q Q -learning with function approximation is one of the most popular methods in reinforcement learning. Though the idea of using function approximation was proposed at least 60 years ago, even in the simplest setup, i.e, approximating Q Q Q -functions with linear functions, it is still an open problem on how to design a pr…
Recently, Petrik et al. demonstrated that L1Regularized Approximate Linear Programming (RALP) could produce value functions and policies which compared favorably to established linear value function approximation techniques like LSPI. RALP's success primarily stems from the ability to solve the feature selection and va…
New algorithm reduces reinforcement learning regret to sqrt(d^3T).
problem Efficient reinforcement learning with generalized linear function approximation.
method Optimistic closure assumption for generalized linear functions.
result Proved regret bound of O(sqrt(d^3T)).
New algorithm for offline RL with linear approx in MDPs and MGs, nearly optimal.
problem Offline RL with linear function approximation in MDPs and MGs.
method Pessimism-based algorithm with uncertainty decomposition via reference function.
result Nearly minimax optimal performance in offline RL for MDPs and MGs.
New RL algorithm tackles nonstationary MDPs with linear approximations and varying rewards.
problem Nonstationary reinforcement learning with evolving reward and state transition functions.
method Developed a new algorithm LSVI-UCB-Restart with periodic restart, and parameter-free Ada-LSVI-UCB-Restart for unknown variation budgets.
result First minimax dynamic regret lower bound for nonstationary linear MDPs and linear MDPs lower bound.
The paper analyzes the convergence rates of Q-learning with entropy regularization and linear function approximation.
problem Analyzing the convergence rates of Q-learning with entropy regularization and linear function approximation.
method The paper derives rates of convergence using the high-dimensional central limit theorem, linearization of the soft Bellman recursion, and Gaussian approximation for the leading martingale term.
result The algorithm's last iterate satisfies high-order moment bounds, with a Gaussian approximation bound of order n − 1 / 4 n^{-1/4} n − 1/4 . Stochastic differential equation approximation for linear TD(0) under Markovian noise
problem Temporal-difference learning with linear function approximation
method Stochastic differential equation approximation
result Explains the constant-stepsize error floor
This paper compares linear regression and neural networks for pricing swing options.
problem Pricing swing options using approximation methods.
method Linear regression and neural networks for approximating the continuation value and swing price.
result The approximation methods converge to the actual swing price as the number of functions or Monte Carlo samples increases.
Improved gap-dependent bounds for reinforcement learning with linear approximations.
problem Achieving nearly minimax-optimal performance with linear function approximation.
method Developed and analyzed the LSVI-UCB++ algorithm and its concurrent variant.
result First gap-dependent regret bound for nearly minimax-optimal algorithm LSVI-UCB++.
Agents learn state ambiguity from non-linear sensor data using Gaussian approximations.
problem Learning state representation from non-linear sensor data.
method Second-order Taylor approximation of Gaussian distribution for non-linear measurement functions.
result Induces a preference for states based on inferability from observations.
Functional input neural networks approximate continuous functions on weighted spaces.
problem Approximating continuous functions on infinite-dimensional weighted spaces.
method Additive family mapping, non-linear activation, linear readouts, Stone-Weierstrass theorem.
result Global universal approximation of continuous functions on weighted spaces.
New algorithm for reward-free RL with linear function approximation, reducing sample complexity.
problem Efficiently learning optimal policies without prior reward information in complex environments.
method Developed an algorithm for reward-free RL in linear Markov decision processes, proving sample complexity bounds.
result Polynomial sample complexity in feature dimension and planning horizon, independent of states and actions.
This work connects hardness of approximation and learning.
problem Hardness of approximation and learnability in machine learning.
method Shows a single hardness property implying both approximation and learning hardness.
result Obtains new results on hardness of approximation and learnability of specific functions.
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.
Algorithm reduces regret in SSP problems with LFA.
problem Finding shortest paths in stochastic environments with linear approximations.
method Uses linear function approximation and stationary policies to minimize regret.
result Achieves sublinear regret under minimal assumptions.
New algorithms for learning MDPs with linear approximations in infinite-horizon settings.
problem Learning infinite-horizon average-reward MDPs with linear function approximation.
method Optimism principle, adversarial linear bandits, Natural Policy Gradient.
result Efficient algorithms with optimal or near-optimal regret bounds.
The paper addresses the invariance issue in Bayesian neural networks using linearized Laplace approximation.
problem Bayesian neural networks fail to maintain invariance under reparameterization, leading to different posterior densities for identical functions.
method Developed a geometric view of reparameterizations and a Riemannian diffusion process to extend reparameterization invariance to neural network predictive.
result Empirically improved posterior fit through approximate posterior sampling.
Polynomial-time RL algorithm for constant actions under linear Bellman completeness.
problem Efficient online reinforcement learning with few actions.
method Polynomial-time algorithm based on linear function approximation.
result First computationally efficient algorithm for RL with constant actions under linear Bellman completeness.
The paper analyzes the sample complexity of offline RL with linear approximations, identifying a hard regime and providing an algorithm.
problem Sample complexity of policy evaluation in infinite-horizon offline reinforcement learning with linear function approximation.
method Identification of a hard regime and construction of hard instances; algorithm with sample complexity bound.
result An algorithm that guarantees approximation to the value function up to an additive error of ε with high probability.
Universal approximation for stochastic processes using Brownian motion.
problem Approximating stochastic processes with linear functionals.
method Establishing L p L^p L p -type universal approximation theorems for rough path spaces. result Linear functionals on the signature of time-extended Brownian motion can approximate any p p p -integrable stochastic process. A linear model approximates Gaussian processes for efficient control.
problem Efficiently modeling and controlling Gaussian processes with many parameters.
method Developed a linear model using basis functions to approximate Gaussian processes.
result The linear model improves computational efficiency and feasibility of control strategies.
SKOLR uses linear RNNs to approximate Koopman operators for time-series forecasting.
problem Nonlinear dynamical system analysis and time-series forecasting with infinite-dimensional Koopman operators.
method Established a connection between Koopman operator approximation and linear RNNs, integrating learnable spectral decomposition and MLP.
result SKOLR delivers exceptional performance in various forecasting benchmarks and dynamical systems.
Paper proposes LANN to measure model complexity of neural networks with curve activation functions.
problem Measuring model complexity of neural networks with curve activation functions.
method Proposes LANN, a piecewise linear framework to approximate curve activation functions, and derives complexity measure based on the number of linear regions.
result Demonstrates positive correlation between overfitting and model complexity during training.
Paper develops efficient RL algorithm for general value function approximation.
problem Lack of theory for RL with general value function approximation.
method Provable efficient RL algorithm using bounded eluder dimension.
result Achieves a regret bound of O ~ ( p o l y ( d H ) T ) \widetilde{O}(\mathrm{poly}(dH)\sqrt{T}) O ( poly ( d H ) T ) . New algorithms for RL in Markov games with independent linear function approximation, breaking the curse of multiagents.
problem Tackles the challenge of learning Markov equilibria in large state space Markov games with multiple agents.
method Proposes independent linear Markov games and designs new algorithms for learning Markov coarse correlated equilibria and Markov correlated equilibria with polynomial sample complexity.
result Breaks the curse of multiagents by achieving sample complexity bounds that scale polynomially with each agent's function class complexity.
Algorithm approximates functions into manifolds with curvature bounds.
problem Approximating functions into manifolds with lower curvature bounds.
method Algorithm using manifold exponential and logarithm, with error bounds based on sectional curvature.
result Error bounds for nonnegative sectional curvature are similar to linear space approximations.
Enhances RL with function approximation, improving regret bounds.
problem Improving exploration in reinforcement learning with function approximation.
method Prior-dependent Bayesian regret bound for PSRL with linear mixture MDPs, using value-targeted model learning and variance reduction.
result Established an upper bound of O ( d H 3 T log T ) {\mathcal{O}}(d\sqrt{H^3 T \log T}) O ( d H 3 T log T ) for PSRL. VO Q Q Q L optimizes RL with sparse rewards using weighted bounds.
problem Sparse rewards and non-linear function approximation in RL.
method VO Q Q Q L combines Q Q Q -learning with weighted bounds for optimal regret. result Achieves asymptotically optimal regret for linear function approximation.
New lower bound shows RL with linear approximations is computationally hard.
problem Computational hardness in reinforcement learning with linear function approximation.
method Reduction from Unique-Sat to MDPs with linear optimal value functions.
result No randomized polynomial time algorithm exists for RL with linear function approximation unless NP=RP.
Proposes a convergent TD algorithm for off-policy RL.
problem Learning value function from different policies in RL.
method Convergent on-policy TD algorithm with linear function approximation.
result Proposes a convergent TD algorithm for off-policy RL.