20 results for “RL algorithms”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Xi Chen, Fengqi Hu, Zeyu Shen, Jiaying Xu +4 more
The paper introduces RobustRLlib, a library and benchmark for robust reinforcement learning that improves reusability and provides an empirical capability map of current robust RL algorithms.
The paper introduces Prompted Policy Optimization (PromptPO), an LLM-based method that successfully optimizes policies for various sequential RL tasks, demonstrating that LLMs can replace classical RL…
Zijian Zhang, Rizhen Hu, Athanasios Glentis, Dawei Li +3 more
This paper studies the distribution of reinforcement learning (RL) adaptation across transformer layers in large language models and finds that training a single layer can recover most of the gains ob…
This paper proposes a continual RL framework based on Continual Backpropagation for autonomous racing, able to train a generalistic policy on a set of tracks and fine-tune it within 15 minutes to outp…
This paper analyzes the convergence of the RLS algorithm using the Cauchy Interlace Theorem and presents an improved initialization method.
This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller m…
Jiasheng Zheng, Boxi Cao, Boxi Yu, Yuzhong Zhang +5 more
The paper introduces Atomic Decomposition and Recombination (ADR), a novel framework that generates genuinely novel and challenging verifiable code tasks, significantly improving the scalability of Re…
This paper introduces a general model of genetic algorithms and studies their optimization problems using reinforcement learning.
The paper presents an algorithm for solving linear programming problems in the oracle model with improved time complexity.
Daniel Dadush, Zhuan Khye Koh, Bento Natura, Neil Olver +1 more
This paper presents an initialization framework and rounding procedure for interior point methods in linear programming, ensuring strongly polynomial time complexity.
This paper provides a counterexample to a claimed linear-time comparison-based algorithm for solving deterministic graphical games (DGGs) and gives a deterministic linear-time reduction from the direc…
This paper improves max-policy iteration by replacing mathematical optimization with value iteration and proposes min-policy iteration as an alternative to linear programming.
This paper rigorously proves that a Reinforcement Learning Hyper-heuristic (RLHH) optimizes the LeadingOnes benchmark function with optimal expected runtime using two random local search operators, ou…
Ya-Qi Yu, Hao Wang, Fangyu Hong, Xiangyang Qu +14 more
The paper introduces $ ext{RLR}^3$, a novel framework that extends verifiable rewards in Reinforcement Learning to handle partially verifiable, multi-criteria vision-language tasks by integrating robu…
This paper reviews models of inexact computational oracles in smooth continuous optimization and their implications for optimization algorithms.
The paper proposes a general approach to augmenting exact exponential-time algorithms for NP-hard problems using machine-learned predictions.