A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Zeyu Zhang, Quanyu Dai, Xiaohe Bo, et al.
A comprehensive survey that systematically reviews the memory mechanisms of LLM-based agents, covering design, evaluation, applications, limitations, and future directions.
Jens Kober, J. Andrew Bagnell, Jan Peters
A comprehensive survey of reinforcement learning for robot behavior generation, highlighting key challenges, successes, and the trade-offs between model-based/model-free and value-function/policy-search methods.
Unknown
This paper provides a sharp theoretical analysis of model-based reinforcement learning with self-play, establishing sample complexity bounds and showing that model-based algorithms can achieve near-optimal performance in competitive environments.
Unknown
This paper introduces a safe model-based reinforcement learning approach that guarantees stability during exploration and learning.
Unknown
A survey of high-accuracy model-based reinforcement learning, covering recent advances and challenges.
Unknown
This paper introduces a model-based reinforcement learning approach via meta-policy optimization to improve data efficiency by learning dynamics models that better match the true environment.
Unknown
This paper studies model-based reinforcement learning for regret minimization in finite-hizon episodic settings with a known transition model family, proposing a value-targeted regression approach.
Unknown
This paper explores model-based reinforcement learning with stochastic predictive models as a promising, efficient alternative to model-free methods for Atari games.
Unknown
Proposes a modular reinforcement learning architecture for nonlinear, nonstationary control tasks using multiple models.
Unknown
This survey reviews model-based reinforcement learning methods that construct environment models to improve sample efficiency and reduce errors.
Unknown
This survey reviews model-based reinforcement learning methods and their applications in robotics, highlighting their advantages and discussing future applicability.
Unknown
This survey provides a comprehensive overview of model-based reinforcement learning, defining its categories and synthesizing recent advances.