Policy

السياسة

في التعلم المعزز، الاستراتيجية التي تربط الحالات بالأفعال. في RLHF، النموذج اللغوي ذاته — يربط الأوامر بالإجابات.

In RL, the strategy that maps states to actions. In RLHF, the language model itself — mapping prompts to responses.

Also translated asاستراتيجية العمل، سياسة التوليد، سياسة النموذج، منهجية الاختيار والترجيح، نموذج السياسة

First appears in this corpus in: The Monte Carlo Method (1949)

Appears in these papers

Asynchronous Methods for Deep Reinforcement Learning2016 in the sky ✦
Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware2023 in the sky ✦
Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware2023 in the sky ✦
Mastering the Game of Go Without Human Knowledge2017 in the sky ✦
Discovering Faster Matrix Multiplication Algorithms with Reinforcement Learning2022 in the sky ✦
A General Reinforcement Learning Algorithm That Masters Chess, Shogi, and Go Through Self-Play2018 in the sky ✦
A General Reinforcement Learning Algorithm That Masters Chess, Shogi, and Go Through Self-Play2018 in the sky ✦
Concrete Problems in AI Safety2016 in the sky ✦
Conservative Q-Learning for Offline Reinforcement Learning2020 in the sky ✦
Continuous Control with Deep Reinforcement Learning2015 in the sky ✦
Deep Reinforcement Learning from Human Preferences2017 in the sky ✦
Deep Reinforcement Learning with Double Q-Learning2016 in the sky ✦
Direct Preference Optimization: Your Language Model Is Secretly a Reward Model2023 in the sky ✦
Human-Level Control Through Deep Reinforcement Learning2015 in the sky ✦
Dueling Network Architectures for Deep Reinforcement Learning2016 in the sky ✦
Dynamic Programming1957 in the sky ✦
High-Dimensional Continuous Control Using Generalized Advantage Estimation2016 in the sky ✦
First Return, Then Explore2021 in the sky ✦
Hindsight Experience Replay2017 in the sky ✦
Curiosity-Driven Exploration by Self-Supervised Prediction2017 in the sky ✦
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures2018 in the sky ✦
Training Language Models to Follow Instructions with Human Feedback2022 in the sky ✦
On Information and Sufficiency1951 in the sky ✦
Learning Dexterous In-Hand Manipulation2019 in the sky ✦
Learning Dexterous In-Hand Manipulation2019 in the sky ✦
Learning to Summarize from Human Feedback2020 in the sky ✦
The Monte Carlo Method1949 in the sky ✦
Natural Gradient Works Efficiently in Learning1998 in the sky ✦
Between MDPs and Semi-MDPs — A Framework for Temporal Abstraction in Reinforcement Learning1999 in the sky ✦
Between MDPs and Semi-MDPs — A Framework for Temporal Abstraction in Reinforcement Learning1999 in the sky ✦
Policy Gradient Methods for Reinforcement Learning with Function Approximation1999 in the sky ✦
Policy Gradient Methods for Reinforcement Learning with Function Approximation1999 in the sky ✦
Proximal Policy Optimization Algorithms2017 in the sky ✦
Prioritized Experience Replay2015 in the sky ✦
Q-Learning1992 in the sky ✦
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation2018 in the sky ✦
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation2018 in the sky ✦
Reflexion: Language Agents with Verbal Reinforcement Learning2023 in the sky ✦
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning1992 in the sky ✦
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback2023 in the sky ✦
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor2018 in the sky ✦
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor2018 in the sky ✦
Optimization by Simulated Annealing1983 in the sky ✦
Temporal Difference Learning and TD-Gammon1995 in the sky ✦
Temporal Difference Learning and TD-Gammon1995 in the sky ✦
End-to-End Training of Deep Visuomotor Policies2016 in the sky ✦
End-to-End Training of Deep Visuomotor Policies2016 in the sky ✦
WebGPT: Browser-Assisted Question-Answering with Human Feedback2021 in the sky ✦
World Models2018 in the sky ✦
World Models2018 in the sky ✦