Reinforcement Learning
Policy Optimization for Robust Average Cost MDPs
Specifically, we focus on ergodic Markov chains.
ORA: Towards Safety Alignment of T ext2Video Generation via a Human Preference Dataset
This dataset encompasses human preferences in text-to-video generation tasks along two primary dimensions: helpfulness and harmlessness.
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
However, safe RL often suffers from sample inefficiency, requiring extensive interactions with the environment to learn a safe policy.
Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence
As AI systems become increasingly sophisticated and interconnected, it will be critical that they be competent at cooperating, both with other AI systems and with humans.
No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery Alex Rutherford Michael Beukman Timon Willi Bruno Lacerda Nick Hawes Jakob Foerster University of Oxford
Put differently, current methods fail to predict intuitive measures of "learnability."
Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning Hao Ma
Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks. However, prevailing RL fine-tuning methods predominantly rely on PPO and its variants. Though these algorithms are effective in general RL settings, they often exhibit suboptimal performance and vulnerability to distribution collapse when applied to the fine-tuning of LLMs.
Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn
Network outputs can change indirectly to unexpected values after any random batch update for input data not included in the batch, called churn in this paper.