Deterministic Policy

Deterministic policy learning in reinforcement learning aims to find optimal action selection strategies that are predictable and repeatable, unlike stochastic policies. Current research focuses on developing efficient algorithms for finding these policies, particularly in continuous state and action spaces, often employing techniques like policy gradient methods, primal-dual approaches, and model predictive control integrated with neural networks (e.g., LSTM networks). These advancements are significant because deterministic policies are often preferred in real-world applications demanding robustness, safety, and traceability, such as robotics and control systems, while also presenting unique challenges for efficient learning.

Papers

October 25, 2024

SAD: State-Action Distillation for In-Context Reinforcement Learning under Random Policies
Weiqin Chen, Santiago Paternain
Reinforcement Learning Context Learning Action Space Mutual Distillation Autoregressive Neural Network Deterministic Policy Behavior Policy

August 27, 2024

Optimization Solution Functions as Deterministic Policies for Offline Reinforcement Learning
Vanshaj Khattar, Ming Jin
Offline Reinforcement Learning Deterministic Policy Semantic Actor

August 19, 2024

Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs
Sergio Rozada, Dongsheng Ding, Antonio G. Marques, Alejandro Ribeiro
Primal Dual Deterministic Policy Deterministic Policy Gradient

July 18, 2024

Deterministic Trajectory Optimization through Probabilistic Optimal Control
Mohammad Mahmoudi Filabadi, Tom Lefebvre, Guillaume Crevecoeur
Optimal Control Trajectory Optimization Finite Horizon Trajectory Optimization Problem Deterministic Policy Probabilistic Control

June 20, 2024

Soft-QMIX: Integrating Maximum Entropy For Monotonic Value Function Factorization
Wentse Chen, Shiyu Huang, Jeff Schneider
Multi Agent Reinforcement Learning Maximum Entropy Deterministic Policy Maximum Entropy Reinforcement Learning Value Function Factorization Soft QMIX

May 29, 2024

Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies
Haanvid Lee, Tri Wahyu Guntara, Jongmin Lee, Yung-Kyun Noh, Kee-Eung Kim
Reinforcement Learning Action Space Policy Evaluation Deterministic Policy Kernel Distance

May 23, 2024

Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time
Jeremy McMahan
Constrained Reinforcement Learning Near Optimal Policy Deterministic Policy Approximate Dynamic Programming Polynomial Time Approximation

May 3, 2024

Learning Optimal Deterministic Policies with Stochastic Policy Gradients
Alessandro Montenegro, Marco Mussi, Alberto Maria Metelli, Matteo Papini
Reinforcement Learning Policy Gradient Deterministic Policy Stochastic Control Stochastic Policy Gradient

January 18, 2024

Generalized Nested Rollout Policy Adaptation with Limited Repetitions
Tristan Cazenave
Deterministic Policy Exercise Repetition RNA Folding Nested Rollout Policy Adaptation

November 30, 2023

The Sliding Regret in Stochastic Bandits: Discriminating Index and Randomized Policies
Victor Boone
One Shot Simple Regret Stochastic Bandit Regret Algorithm Deterministic Policy Discriminative Response

November 9, 2023

Anytime-Constrained Reinforcement Learning
Jeremy McMahan, Xiaojin Zhu
Markov Decision Process Optimal Policy Constrained Reinforcement Learning Constrained Markov Decision Process Deterministic Policy Markovian Policy

August 28, 2023

Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning
Hanhan Zhou, Tian Lan, Vaneet Aggarwal
Reinforcement Learning Offline Reinforcement Learning Policy Evaluation Deterministic Policy

July 22, 2023

On the Expressivity of Multidimensional Markov Reward
Shuwa Miura
Markov Decision Process Reward Function Sequential Decision Behavior Expressivity Style Deterministic Policy Markovian Reward

July 18, 2023

Mining of Single-Class by Active Learning for Semantic Segmentation
Hugues Lambert, Emma Slade
Semantic Segmentation Deep Reinforcement Learning Active Learning True Class Mining Complex Deterministic Policy Performing Model

May 11, 2023

Policy Gradient Algorithms Implicitly Optimize by Continuation
Adrien Bolland, Gilles Louppe, Damien Ernst
Reinforcement Learning Policy Gradient Deterministic Policy Policy Gradient Algorithm Direct Policy Gaussian Policy

March 29, 2023

Learning Complicated Manipulation Skills via Deterministic Policy with Limited Demonstrations
Liu Haofeng, Chen Yiwen, Tan Jiayi, Marcelo H Ang
Reinforcement Learning Deep Reinforcement Learning Serial Manipulator Deterministic Policy Complex Manipulation

February 21, 2023

UAV Path Planning Employing MPC- Reinforcement Learning Method Considering Collision Avoidance
Mahya Ramezani, Hamed Habibi, Jose luis Sanchez Lopez, Holger Voos
Reinforcement Learning Predictive Control Collision Avoidance Deep Deterministic Policy Gradient Deterministic Policy UAV Path Planning

February 7, 2023

MACOptions: Multi-Agent Learning with Centralized Controller and Options Framework
Alakh Aggarwal, Rishita Bansal, Parth Padalkar, Sriraam Natarajan
Multi Agent Task Planning Q Learning Multi Agent Learning Deterministic Policy Mac Advice

December 1, 2022

Deterministic Policy

Papers

SAD: State-Action Distillation for In-Context Reinforcement Learning under Random Policies

Optimization Solution Functions as Deterministic Policies for Offline Reinforcement Learning

Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs

Deterministic Trajectory Optimization through Probabilistic Optimal Control

Soft-QMIX: Integrating Maximum Entropy For Monotonic Value Function Factorization

Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies

Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time

Learning Optimal Deterministic Policies with Stochastic Policy Gradients

Generalized Nested Rollout Policy Adaptation with Limited Repetitions

The Sliding Regret in Stochastic Bandits: Discriminating Index and Randomized Policies

Anytime-Constrained Reinforcement Learning

Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning

On the Expressivity of Multidimensional Markov Reward

Mining of Single-Class by Active Learning for Semantic Segmentation

Policy Gradient Algorithms Implicitly Optimize by Continuation

Learning Complicated Manipulation Skills via Deterministic Policy with Limited Demonstrations

UAV Path Planning Employing MPC- Reinforcement Learning Method Considering Collision Avoidance

MACOptions: Multi-Agent Learning with Centralized Controller and Options Framework

Nonlinear controllability and function representation by neural stochastic differential equations

Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP