No article text was recorded for this version.
linear function approximation constraint
Version 2 of 21,456 papers1,592 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Finite Sample Analyses for TD(0) with Function Approximation
- Blog: Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime
- Blog: Backstepping Temporal Difference Learning
- Blog: Model-Free Robust Reinforcement Learning with Linear Function Approximation
- Blog: On the Convergence and Sample Complexity Analysis of Deep Q-Networks with ε-Greedy Exploration
- Blog: Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation
- Blog: Distributional reinforcement learning with linear function approximation
- Blog: Backstepping Temporal Difference Learning
- Blog: Nonlinear Distributional Gradient Temporal-Difference Learning
- Blog: Stochastic Convergence Results for Regularized Actor-Critic Methods
- Blog: Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
- Blog: Finite Sample Analysis of the GTD Policy Evaluation Algorithms in Markov Setting
- Blog: Finite-Time Analysis of Actor-Critic Methods with Deep Neural Network Approximation
- Blog: A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence
- Blog: Bellman Residual Orthogonalization for Offline Reinforcement Learning
- Blog: Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension
- Blog: Optimism in Reinforcement Learning with Generalized Linear Function Approximation
- Blog: Temporal-difference learning with nonlinear function approximation: lazy training and mean field regimes
- Blog: Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise
- Blog: Anti-Concentrated Confidence Bonuses For Scalable Exploration
- Blog: Target-based temporal difference learning,
- Blog: Provably Correct Optimization and Exploration with Non-linear Policies
- Blog: Zap Q-Learning With Nonlinear Function Approximation
- Blog: Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap
- Blog: Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation
- Blog: Federated Reinforcement Learning: Linear Speedup Under Markovian Sampling
- Blog: Nonasymptotic CLT and Error Bounds for Two-Time-Scale Stochastic Approximation
- Blog: TD Convergence: An Optimization Perspective
- Blog: Convergent Tree-Backup and Retrace with Function Approximation
- Blog: Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games
- Blog: HEX and Neurodynamic Programming
- Blog: Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
- Blog: Optimal Matrix Momentum Stochastic Approximation and Applications to Q-learning
- Blog: A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning
- Blog: A Unifying Framework of Off-Policy General Value Function Evaluation
- Blog: A reinforcement learning approach to hybrid control design
- Blog: A constrained optimization perspective on actor-critic algorithms and application to network routing
- Blog: Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs
- Blog: Provably Efficient Reinforcement Learning with General Value Function Approximation
- Blog: Offline Reinforcement Learning with Differential Privacy
- Blog: Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning
- Blog: Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation
- Blog: Towards painless policy optimization for constrained MDPs
- Blog: Provably Efficient Policy Gradient Methods for Two-Player Zero-Sum Markov Games
- Blog: Decentralized Deterministic Multi-Agent Reinforcement Learning
- Blog: Decentralized multi-agent reinforcement learning with networked agents: recent advances
- Blog: Alternative Function Approximation Parameterizations for Solving Games: An Analysis of f-Regression Counterfactual Regret Minimization
- Blog: Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation
- Blog: Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent
- Blog: Concentration Bounds for Two Timescale Stochastic Approximation with Applications to Reinforcement Learning
- Blog: Making Linear MDPs Practical via Contrastive Representation Learning
- Blog: PID Accelerated Value Iteration Algorithm
- Blog: On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning
- Blog: Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
- Blog: A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms
- Blog: On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces
- Blog: Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning
- Blog: On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations
- Blog: Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes
- Blog: On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization
Showing 60 of 1,456 papers.
History & citation
Current · Permanent link
- Temporal Difference Learning with Redundant Features merged into this direction (64% overlap)
- Two Time Scale Stochastic Approximation merged into this direction (67% overlap)
- Uniform-PAC Bounds and Asymptotic Optimality in Reinforcement Learning merged into this direction (64% overlap)
- Gradient Descent on the Bellman Error for Stable Learning merged into this direction (54% overlap)
- projection-free convergence split from this direction (53% overlap)
- limitation to linear function approximation split from this direction (100% overlap)
- geometric step-size scheduling split from this direction (56% overlap)
- primal-dual saddle-point formulation split from this direction (71% overlap)
- simultaneous actor-critic optimization split from this direction (58% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_linear_function_approximation_constraint_1e6d16d7,
title = {linear function approximation constraint},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/linear-function-approximation-constraint/rdr_1e6d16d771fa48228d33c1640f371980},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_linear_function_approximation_constraint_1e6d16d7_v2,
title = {linear function approximation constraint},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/linear-function-approximation-constraint/rdr_1e6d16d771fa48228d33c1640f371980/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}