REINFORCEMENT-LEARNINGCURRENT2026-06-17

Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation

Seyed Alireza Azimi, Homayoon Farrahi, Abhishek Naik, Colin Bellinger, A. Rupam Mahmood

When Robot LearningTrainingThe process of fitting a model using data or experience. a Manipulation & TasksManipulationUsing a robot arm or hand to move or interact with objects. Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. with Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards., the way you represent actions (Movement, Mechanics & Robot BodyJointA movable connection between robot parts. velocities vs pose increments vs position commands) dramatically changes whether your Core ConceptsPolicyThe rule or model that maps observations or states to actions. transfers from Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested. to real hardware. This paper benchmarks these choices on picking and pushing, showing Movement, Mechanics & Robot BodyJointA movable connection between robot parts. Movement, Mechanics & Robot BodyVelocityHow fast something moves. wins—directly telling developers which Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. formulation to use for their Simulation & Sim-to-RealSim-to-real (sim2real)Transferring a policy trained in simulation to a real robot. pipeline.

THE PROBLEM

This paper focuses on Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards.. When Robot LearningTrainingThe process of fitting a model using data or experience. a Manipulation & TasksManipulationUsing a robot arm or hand to move or interact with objects. Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. with Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards., the way you represent actions (Movement, Mechanics & Robot BodyJointA movable connection between robot parts. velocities vs pose increments vs position commands) dramatically changes whether your Core ConceptsPolicyThe rule or model that maps observations or states to actions. transfers from Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested. to real hardware. This paper benchmarks these choices on picking and pushing, showing Movement, Mechanics & Robot BodyJointA movable connection between robot parts. Movement, Mechanics & Robot BodyVelocityHow fast something moves. wins—directly telling developers which Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. formulation to use for their Simulation & Sim-to-RealSim-to-real (sim2real)Transferring a policy trained in simulation to a real robot. pipeline. Read the paper by tracking the Core ConceptsTaskThe job the robot is supposed to complete, such as pick-and-place, navigation, or drawer opening. definition, the Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. or data assumptions, and the evidence that supports the claimed improvement.

HOW IT WORKS

1

Task framing

The paper frames the work as Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards.. Start here because it defines what success means and which assumptions the rest of the method inherits.

2

Core method

When Robot LearningTrainingThe process of fitting a model using data or experience. a Manipulation & TasksManipulationUsing a robot arm or hand to move or interact with objects. Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. with Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards., the way you represent actions (Movement, Mechanics & Robot BodyJointA movable connection between robot parts. velocities vs pose increments vs position commands) dramatically changes whether your Core ConceptsPolicyThe rule or model that maps observations or states to actions. transfers from Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested. to real hardware. This paper benchmarks these choices on picking and pushing, showing Movement, Mechanics & Robot BodyJointA movable connection between robot parts. Movement, Mechanics & Robot BodyVelocityHow fast something moves. wins—directly telling developers which Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. formulation to use for their Simulation & Sim-to-RealSim-to-real (sim2real)Transferring a policy trained in simulation to a real robot. pipeline. When reading the method section, identify the inputs, the learned or engineered representation, and the Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. or prediction produced by the system.

3

Data and supervision

For robotics work, the data story is part of the method: check whether the system depends on Imitation & Reinforcement LearningTeleoperation (teleop)A human remotely controlling the robot, often to collect demonstrations., Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested., internet video, human labels, or Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. rollouts.

4

Evaluation evidence

The paper should be judged through its Simulation & Sim-to-RealEvaluationMeasuring how well a robot system performs. protocol: what data is used, what Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. or simulator is tested, and which Evaluation & ResearchBaselineA reference method used for comparison. comparisons support the claim. Look for the gap between the headline result and the Simulation & Sim-to-RealDeploymentPutting the trained system on a real robot. setting you would actually care about.

KEY RESULTS

Main contributionConceptual contribution

When Robot LearningTrainingThe process of fitting a model using data or experience. a Manipulation & TasksManipulationUsing a robot arm or hand to move or interact with objects. Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. with Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards., the way you represent actions (Movement, Mechanics & Robot BodyJointA movable connection between robot parts. velocities vs pose increments vs position commands) dramatically changes whether your Core ConceptsPolicyThe rule or model that maps observations or states to actions. transfers from Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested. to real hardware. This paper benchmarks these choices on picking and pushing, showing Movement, Mechanics & Robot BodyJointA movable connection between robot parts. Movement, Mechanics & Robot BodyVelocityHow fast something moves. wins—directly telling developers which Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. formulation to use for their Simulation & Sim-to-RealSim-to-real (sim2real)Transferring a policy trained in simulation to a real robot. pipeline.

WHY DEVELOPERS SHOULD CARE

When Robot LearningTrainingThe process of fitting a model using data or experience. a Manipulation & TasksManipulationUsing a robot arm or hand to move or interact with objects. Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. with Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards., the way you represent actions (Movement, Mechanics & Robot BodyJointA movable connection between robot parts. velocities vs pose increments vs position commands) dramatically changes whether your Core ConceptsPolicyThe rule or model that maps observations or states to actions. transfers from Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested. to real hardware. This paper benchmarks these choices on picking and pushing, showing Movement, Mechanics & Robot BodyJointA movable connection between robot parts. Movement, Mechanics & Robot BodyVelocityHow fast something moves. wins—directly telling developers which Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. formulation to use for their Simulation & Sim-to-RealSim-to-real (sim2real)Transferring a policy trained in simulation to a real robot. pipeline.

LIMITATIONS

The main limitation to check is whether the claimed behavior holds outside the paper's reported setup. That means testing across different Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. embodiments, scenes, objects, and data distributions.

WHAT COMES NEXT

The practical next step is independent reproduction with clear baselines, ablations, and stress tests. For a developer, the useful follow-up is to map the paper's Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. assumptions onto a concrete Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. stack, then test the smallest version of the method that could run end to end.

RELATED PAPERS