No article text was recorded for this version.
asymptotic performance gap
Version 1 of 1117 papers122 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Sample-Efficient Imitation Learning via Generative Adversarial Nets
- Blog: Generalised Policy Improvement with Geometric Policy Composition
- Blog: SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning
- Blog: Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies
- Blog: Model Based Reinforcement Learning for Atari
- Blog: How to Train PointGoal Navigation Agents on a (Sample and Compute) Budget
- Blog: Hindsight Goal Ranking on Replay Buffer for Sparse Reward Environment
- Blog: An Algorithmic Perspective on Imitation Learning
- Blog: Generalised Policy Improvement with Geometric Policy Composition
- Blog: Representation Transfer via Elaboration
- Blog: Policy Gradient Methods in the Presence of Symmetries and State Abstractions
- Blog: Accelerating Model-Free Policy Optimization Using Model-Based Gradient: A Composite Optimization Perspective
- Blog: SpeedyZero: Mastering Atari with Limited Data and Time
- Blog: Variational Model-based Policy Optimization
- Blog: Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning
- Blog: Exploring Model-based Planning with Policy Networks
- Blog: Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
- Blog: DIFFER:Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning
- Blog: On the model-based stochastic value gradient for continuous reinforcement learning
- Blog: Predictive representations can link model-based reinforcement learning to model-free mechanisms
- Blog: Q-Cogni: An Integrated Causal Reinforcement Learning Framework
- Blog: Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
- Blog: OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control
- Blog: Fast deep reinforcement learning using online adjustments from the past
- Blog: Active Advantage-Aligned Online Reinforcement Learning with Offline Data
- Blog: BASE: Bridging the Gap between Cost and Latency for Query Optimization
- Blog: Hybrid Control for Learning Motor Skills
- Blog: Randomized Ensembled Double Q-Learning: Learning Fast Without a Model
- Blog: Policy Newton Algorithm in Reproducing Kernel Hilbert Space
- Blog: Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance
- Blog: Deep Reinforcement and InfoMax Learning
- Blog: Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels
- Blog: The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
- Blog: Approximate Dynamic Programming Finally Performs Well in the Game of Tetris
- Blog: Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
- Blog: Accelerating Model-Based Reinforcement Learning with State-Space World Models
- Blog: Learning Policies from Human Data for Skat
- Blog: A Computational Framework for Motor Skill Acquisition
- Blog: Constrained Policy Optimization via Bayesian World Models
- Blog: Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse
- Blog: Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation
- Blog: Inverse Reinforcement Learning with Explicit Policy Estimates
- Blog: Solving Complex Manipulation Tasks with Model-Assisted Model-Free Reinforcement Learning
- Blog: Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization
- Blog: Value-of-Information based Arbitration between Model-based and Model-free Control
- Blog: Control as Hybrid Inference
- Blog: Simplicial Embeddings Improve Sample Efficiency in Actor–Critic Agents
- Blog: How to reduce computation time while sparing performance during robot navigation? A neuro-inspired architecture for autonomous shifting between model-based and model-free learning
- Blog: A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning
- Blog: Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier
- Blog: A Unified Theoretical Framework for Cognitive Sequencing
- Blog: Maximum Entropy Model Correction in Reinforcement Learning
- Blog: Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning
- Blog: Imagination-Augmented Agents for Deep Reinforcement Learning
- Blog: The successor representation in human reinforcement learning
- Blog: FM-EAC: Feature Model-based Enhanced Actor-Critic for Multi-Task Control in Dynamic Environments
- Blog: Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization
- Blog: Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL
- Blog: Pathfinding in stochastic environments: learning vs planning
- Blog: Is Q-Learning Provably Efficient?
Showing 60 of 117 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_asymptotic_performance_gap_7fb8db16,
title = {asymptotic performance gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/asymptotic-performance-gap/rdr_7fb8db161fa6441c9f912ff26f7bdcbc},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_asymptotic_performance_gap_7fb8db16_v1,
title = {asymptotic performance gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/asymptotic-performance-gap/rdr_7fb8db161fa6441c9f912ff26f7bdcbc/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}