Summary of Enhancing Llm Safety Via Constrained Direct Preference Optimization, by Zixuan Liu et al.
Enhancing LLM Safety via Constrained Direct Preference Optimizationby Zixuan Liu, Xiaolin Sun, Zizhan ZhengFirst submitted…
Summary of Koopman-assisted Reinforcement Learning, by Preston Rozwood et al.
Koopman-Assisted Reinforcement Learningby Preston Rozwood, Edward Mehrez, Ludger Paehler, Wen Sun, Steven L. BruntonFirst submitted…
Summary of Towards Provable Log Density Policy Gradient, by Pulkit Katdare et al.
Towards Provable Log Density Policy Gradientby Pulkit Katdare, Anant Joshi, Katherine Driggs-CampbellFirst submitted to arxiv…
Summary of Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks, by Ziping Xu et al.
Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasksby Ziping Xu, Zifan Xu,…
Summary of On the Role Of Information Structure in Reinforcement Learning For Partially-observable Sequential Teams and Games, by Awni Altabaa et al.
On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Gamesby…
Summary of Continuous Mean-zero Disagreement-regularized Imitation Learning (cmz-dril), by Noah Ford et al.
Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)by Noah Ford, Ryan W. Gardner, Austin Juhl, Nathan LarsonFirst…
Summary of Efficient Episodic Memory Utilization Of Cooperative Multi-agent Reinforcement Learning, by Hyungho Na et al.
Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learningby Hyungho Na, Yunkyeong Seo, Il-chul MoonFirst…
Summary of Direct Alignment Of Draft Model For Speculative Decoding with Chat-fine-tuned Llms, by Raghavv Goel et al.
Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMsby Raghavv Goel, Mukul Gagrani,…
Summary of Efficientzero V2: Mastering Discrete and Continuous Control with Limited Data, by Shengjie Wang et al.
EfficientZero V2: Mastering Discrete and Continuous Control with Limited Databy Shengjie Wang, Shaohuai Liu, Weirui…
Summary of Reusing Historical Trajectories in Natural Policy Gradient Via Importance Sampling: Convergence and Convergence Rate, by Yifan Lin et al.
Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rateby Yifan…