Order-Optimal Instance-Dependent Bounds for Offline Reinforcement Learning with Preference Feedbackby Zhirui Chen, Vincent Y. F.…
More Efficient Randomized Exploration for Reinforcement Learning via Approximate Samplingby Haque Ishfaq, Yixin Tan, Yu…
Demystifying the Recency Heuristic in Temporal-Difference Learningby Brett Daley, Marlos C. Machado, Martha WhiteFirst submitted…
Is poisoning a real threat to LLM alignment? Maybe more so than you thinkby Pankayaraj…
Adding Conditional Control to Diffusion Models with Reinforcement Learningby Yulai Zhao, Masatoshi Uehara, Gabriele Scalia,…
Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Plannerby Kenneth Li,…
The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximationby Noah…
Measuring memorization in RLHF for code completionby Aneesh Pappu, Billy Porter, Ilia Shumailov, Jamie HayesFirst…
Optimal Transport-Assisted Risk-Sensitive Q-Learningby Zahra Shahrooei, Ali BaheriFirst submitted to arxiv on: 17 Jun 2024CategoriesMain:…
Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamicsby Runzhe Wu, Ayush Sekhari, Akshay…