No article text was recorded for this version.
extrapolation error (out-of-distribution value overestimation)
Version 2 of 2370 papers421 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Benchmarking Batch Deep Reinforcement Learning Algorithms
- Blog: Measuring and Characterizing Generalization in Deep Reinforcement Learning
- Blog: Benchmarking Batch Deep Reinforcement Learning Algorithms
- Blog: Off-Policy Deep Reinforcement Learning without Exploration
- Blog: Offline Quantum Reinforcement Learning in a Conservative Manner
- Blog: Offline policy optimization with eligible actions
- Blog: The Difficulty of Passive Learning in Deep Reinforcement Learning
- Blog: Offline Evaluation for Reinforcement Learning-based Recommendation: A Critical Issue and Some Alternatives
- Blog: Challenges for Reinforcement Learning in Healthcare
- Blog: Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
- Blog: ACTIVE: Offline Reinforcement Learning via Adaptive Imitation and In-sample $V$-Ensemble
- Blog: Bandit Overfitting in Offline Policy Learning
- Blog: Conservative Offline Goal-Conditioned Implicit V-Learning
- Blog: Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data
- Blog: State Advantage Weighting for Offline RL
- Blog: Model Generation with Provable Coverability for Offline Reinforcement Learning
- Blog: Offline Reinforcement Learning with Value-based Episodic Memory
- Blog: Constrained GPI for Zero-Shot Transfer in Reinforcement Learning
- Blog: RL4RS: A Real-World Benchmark for Reinforcement Learning based Recommender System
- Blog: Avoiding Overfitting to the Importance Weights in Offline Policy Optimization
- Blog: Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flow
- Blog: Medical Dead-ends and Learning to Identify High-Risk States and Treatments
- Blog: A Dataset Perspective on Offline Reinforcement Learning
- Blog: Offline Reinforcement Learning with Mixture of Deterministic Policies
- Blog: Offline Reinforcement Learning as Anti-Exploration
- Blog: Behavior Proximal Policy Optimization
- Blog: Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning
- Blog: For SALE: State-Action Representation Learning for Deep Reinforcement Learning
- Blog: State Combinatorial Generalization In Decision Making With Conditional Diffusion Models
- Blog: Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy
- Blog: Medical Dead-ends and Learning to Identify High-risk States and\n Treatments
- Blog: Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning
- Blog: Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data
- Blog: Critic-Guided Decision Transformer for Offline Reinforcement Learning
- Blog: A General Offline Reinforcement Learning Framework for Interactive Recommendation
- Blog: Off-Policy Deep Reinforcement Learning without Exploration
- Blog: Continuous Doubly Constrained Batch Reinforcement Learning
- Blog: Regularized Behavior Value Estimation
- Blog: Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data
- Blog: For SALE: State-Action Representation Learning for Deep Reinforcement Learning
- Blog: Semi-Markov Offline Reinforcement Learning for Healthcare
- Blog: Distance-Sensitive Offline Reinforcement Learning
- Blog: Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
- Blog: A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning
- Blog: MADiff: Offline Multi-agent Learning with Diffusion Models
- Blog: Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning
- Blog: C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning
- Blog: Zero-Shot Reinforcement Learning from Low Quality Data
- Blog: Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
- Blog: DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
- Blog: CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning
- Blog: Offline Reinforcement Learning with Pseudometric Learning
- Blog: Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning
- Blog: Keep Doing What Worked: Behavior Modelling Priors for Offline Reinforcement Learning
- Blog: EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
- Blog: FOSP: Fine-tuning Offline Safe Policy through World Models
- Blog: A General Offline Reinforcement Learning Framework for Interactive Recommendation
- Blog: Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning
- Blog: Model-enhanced Contrastive Reinforcement Learning for Sequential Recommendation
- Blog: Improving Offline Reinforcement Learning with Inaccurate Simulators
Showing 60 of 370 papers.
History & citation
Current · Permanent link
- In-Sample Value Estimation via Expectile Regression merged into this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_extrapolation_error_out_of_distribution__f6ab0eae,
title = {extrapolation error (out-of-distribution value overestimation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/extrapolation-error-out-of-distribution-value-overestimation/rdr_f6ab0eae53734743946d09ca24b000ca},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_extrapolation_error_out_of_distribution__f6ab0eae_v2,
title = {extrapolation error (out-of-distribution value overestimation)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/extrapolation-error-out-of-distribution-value-overestimation/rdr_f6ab0eae53734743946d09ca24b000ca/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}