We propose a new approach to increase inference performance in environments that require a specific sequence of actions in order to be solved. This is for example the case for maze environments where ideally an optimal path is determined. Instead of learning a policy for a single step, we want to learn a policy that can predict n actions in advance. Our proposed method called policy horizon regression (PHR) uses knowledge of the environment sampled by A2C to learn an n dimensional policy vector in a policy distillation setup which yields n sequential actions per observation. We test our method on the MiniGrid and Pong environments and show drastic speedup during inference time by successfully predicting sequences of actions on a single observation.
Complexity-Aware Deep Symbolic Regression with Robust Risk-Seeking Policy Gradients
Kahlert School of Computing(卡勒特计算学院);Scientific Computing and Imaging Institute(科学计算与成像研究所);Department of Mechanical Engineering, University of Utah(犹他大学机械工程系)
POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition
Cornell University(康奈尔大学);University of Washington(华盛顿大学);Paul G. Allen School of Computer Science & Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院)
Distributional Off-Policy Evaluation with Deep Quantile Process Regression
School of Statistics and Data Science, and Philosophy and Social Sciences Laboratory of Data Science in Finance and Economics at the Ministry of Education, Jiangxi University of Finance and Economics(统计学与数据科学学院,暨教育部金融与经济数据科学与社会科学实验室,江西财经大学);School of Statistics and Data Science, Shanghai University of Finance and Economics(统计学与数据科学学院,上海财经大学);School of Artificial Intelligence, and Hubei Key Laboratory of Computational Science, Wuhan University(人工智能学院,湖北省计算科学重点实验室,武汉大学)
Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning
Hong Kong University of Science and Technology(香港科技大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Southern University of Science and Technology(南方科技大学)
Vanilla Policy Optimization Is Both Optimal and Differentially Private for Stochastic Contextual Bandits
University of Illinois Chicago(伊利诺伊大学芝加哥分校);Toyota Technological Institute at Chicago(芝加哥丰田技术研究所);Tel Aviv University(特拉维夫大学);University of Toronto(多伦多大学);Vector Institute(向量研究所);Google Research(谷歌研究院)
Efficient Offline Learning of Ranking Policies via Top-$k$ Policy Decomposition
Institute of Science Tokyo(东京科学大学);Keio University(庆应义塾大学);Cornell University(康奈尔大学);Yale University(耶鲁大学);LY Corporation;Hanjuku-kaso, Co., Ltd.(Hanjuku-kaso株式会社)
College of AI & School of Vehicle and Mobility, Tsinghua University(人工智能学院与车辆与移动系统学院,清华大学);Berkeley AI Research (BAIR), UC Berkeley(伯克利人工智能研究(BAIR),加州大学伯克利分校)
REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge
University of California, Los Angeles(加州大学洛杉矶分校);The University of Texas at Austin(得克萨斯大学奥斯汀分校);Google Research Now at Google DeepMind(谷歌研究 现在在谷歌深Mind)
A KL-regularization Framework for Learning to Plan with Adaptive Priors
LIACS, Leiden University, Leiden, The Netherlands(莱顿大学莱顿分校,荷兰);Google Deepmind, London, United Kingdom(谷歌DeepMind,英国伦敦);University of Oxford, Oxford, United Kingdom(牛津大学,英国牛津)
Kahlert School of Computing(卡勒特计算学院);Scientific Computing and Imaging Institute(科学计算与成像研究所);Department of Mechanical Engineering(机械工程系);University of Utah(犹他大学)
Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression
Westlake University(西湖大学);Tsinghua University(清华大学);University of Oxford(牛津大学);Southwest University of Science and Technology(西南科技大学);New Jersey Institute of Technology(新泽西理工学院)
Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments