Action Space

Action space, in reinforcement learning, refers to the set of all possible actions an agent can take within an environment. Current research focuses on efficiently handling large or complex action spaces, particularly in multi-agent systems and continuous control problems, employing techniques like action discretization, factorization, and the use of large language models for guidance. These advancements are crucial for scaling reinforcement learning to real-world applications, such as robotics and resource management, where high-dimensional and nuanced action choices are common. Improved methods for handling action spaces directly impact the sample efficiency and overall performance of reinforcement learning algorithms.

Papers

April 26, 2023

CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing
Philipp Altmann, Fabian Ritz, Leonard Feuchtinger, Jonas Nüßlein, Claudia Linnhoff-Popien, Thomy Phan
Reinforcement Learning Strong Generalization Action Space Policy OpTimization Distributionally Robust

April 25, 2023

A Closer Look at Reward Decomposition for High-Level Robotic Explanations
Wenhao Lu, Xufeng Zhao, Sven Magg, Martin Gromniak, Mengdi Li, Stefan Wermter
Reinforcement Learning Action Space Glance Annotation High Level Explainable Reinforcement Learning Robot Explanation rEward Decomposition

April 24, 2023

April 19, 2023

Torque-based Deep Reinforcement Learning for Task-and-Robot Agnostic Learning on Bipedal Robots Using Sim-to-Real Transfer
Donghyeon Kim, Glen Berseth, Mathew Schwartz, Jaeheung Park
Deep Reinforcement Learning Action Space Formality Transfer Bipedal Robot Task Agnostic

April 8, 2023

Pick2Place: Task-aware 6DoF Grasp Estimation via Object-Centric Perspective Affordance
Zhanpeng He, Nikhil Chavan-Dafle, Jinwook Huh, Shuran Song, Volkan Isler
Action Space Affordance Learning Grasp Anything Pick and Place Task Aware Grasp Estimation Grasp Accuracy

April 7, 2023

Learning Robot Manipulation from Cross-Morphology Demonstration
Gautam Salhotra, I-Chun Arthur Liu, Gaurav Sukhatme
Imitation Learning Action Space Deformable Object Robot Manipulation Suboptimal Demonstration Morphological Exemplar

April 5, 2023

Constrained Exploration in Reinforcement Learning with Optimality Preservation
Peter C. Y. Chen
Reinforcement Learning Action Space Near Optimality Reinforcement Learning System Constrained Exploration

April 3, 2023

March 20, 2023

Deceptive Reinforcement Learning in Model-Free Domains
Alan Lewis, Tim Miller
Reinforcement Learning Action Space State Action Space

March 7, 2023

March 3, 2023

Nature's Cost Function: Simulating Physics by Minimizing the Action
Tim Strang, Isabella Caruso, Sam Greydanus
Ground Truth Action Space Value Function Action Feature Landscape Image Physical Simulation Quantum Simulator Energy Shaping

February 23, 2023

February 21, 2023

Adaptive Discretization using Voronoi Trees for Continuous POMDPs
Marcus Hoerger, Hanna Kurniawati, Dirk Kroese, Nan Ye
Markov Decision Process Action Space Monte Carlo Tree Search Partially Observable Markov Decision Process Voronoi Tessellation Online POMDP Solver Adaptive Discriminative Discretization

February 16, 2023

Linear Bandits with Memory: from Rotting to Rising
Giulia Clerici, Pierre Laforgue, Nicolò Cesa-Bianchi
Action Space Memory Trace Linear Bandit Bandit Model

February 10, 2023

Learning cooperative behaviours in adversarial multi-agent systems
Ni Wang, Gautham P. Das, Alan G. Millard
LeArning Abstract Multi Agent Multi Agent System Action Space Deep Deterministic Policy Gradient Cooperative Behavior Hybrid Reward

February 8, 2023

Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning
Volodymyr Tkachuk, Seyed Alireza Bakhtiari, Johannes Kirschner, Matej Jusup, Ilija Bogunovic, Csaba Szepesvári
Reinforcement Learning Financial Application Action Space Cooperative Multi Agent Reinforcement Learning Efficient Planning Global Reward Blow Up Algorithm

Action Space

Papers

CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing

A Closer Look at Reward Decomposition for High-Level Robotic Explanations

Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics

Efficient Robot Skill Learning with Imitation from a Single Video for Contact-Rich Fabric Manipulation

Torque-based Deep Reinforcement Learning for Task-and-Robot Agnostic Learning on Bipedal Robots Using Sim-to-Real Transfer

Pick2Place: Task-aware 6DoF Grasp Estimation via Object-Centric Perspective Affordance

Learning Robot Manipulation from Cross-Morphology Demonstration

Constrained Exploration in Reinforcement Learning with Optimality Preservation

Action Pick-up in Dynamic Action Space Reinforcement Learning

Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agents

Deceptive Reinforcement Learning in Model-Free Domains

Diffusion Policy: Visuomotor Policy Learning via Action Diffusion

Decoupling Skill Learning from Robotic Control for Generalizable Object Manipulation

Nature's Cost Function: Simulating Physics by Minimizing the Action

Diverse Policy Optimization for Structured Action Space

Revisiting the Gumbel-Softmax in MADDPG

Adaptive Discretization using Voronoi Trees for Continuous POMDPs

Linear Bandits with Memory: from Rotting to Rising

Learning cooperative behaviours in adversarial multi-agent systems

Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning