# Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration

arXiv: https://arxiv.org/abs/2308.02459 · HTML: https://mlsanity.com/paper/2308.02459/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 4 Aug 2023.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [Learning robust perceptive locomotion for quadrupedal robots in the wild](https://mlsanity.com/paper/2201.08117/) (2022)
- [Emergence of Locomotion Behaviours in Rich Environments](https://mlsanity.com/paper/1707.02286/) (2017)
- [Discretizing Continuous Action Space for On-Policy Optimization](https://mlsanity.com/paper/1901.10500/) (2019)
- [Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system](https://mlsanity.com/paper/1803.10371/) (2018)
- [Non-prehensile Planar Manipulation via Trajectory Optimization with Complementarity Constraints](https://mlsanity.com/paper/2109.13145/) (2021)
- [A probabilistic data-driven model for planar pushing](https://mlsanity.com/paper/1704.03033/) (2017)
- [ROS-PyBullet Interface: A Framework for Reliable Contact Simulation and Human-Robot Interaction](https://mlsanity.com/paper/2210.06887/) (2022)
- [Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer](https://mlsanity.com/paper/1910.09471/) (2019)
- [OpTaS: An Optimization-based Task Specification Library for Trajectory Optimization and Model Predictive Control](https://mlsanity.com/paper/2301.13512/) (2023)
- [A Convex Polynomial Force-Motion Model for Planar Sliding: Identification and Application](https://mlsanity.com/paper/1602.06056/) (2016)
- [Demonstration-guided Optimal Control for Long-term Non-prehensile Planar Manipulation](https://mlsanity.com/paper/2212.12814/) (2022)

## Built on by (most cited first, 9 of 9)

- [Flow Matching Imitation Learning for Multi-Support Manipulation](https://mlsanity.com/paper/2407.12381/) (2024)
- [CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects](https://mlsanity.com/paper/2403.10760/) (2024)
- [Learning Visuotactile Estimation and Control for Non-prehensile Manipulation under Occlusions](https://mlsanity.com/paper/2412.13157/) (2024)
- [Dynamic object goal pushing with mobile manipulators through model-free constrained reinforcement learning](https://mlsanity.com/paper/2502.01546/) (2025)
- [Can Context Bridge the Reality Gap? Sim-to-Real Transfer of Context-Aware Policies](https://mlsanity.com/paper/2511.04249/) (2025)
- [Enabling robots to follow abstract instructions and complete complex dynamic tasks](https://mlsanity.com/paper/2406.11231/) (2024)
- [A Reinforcement Learning Approach to Non-prehensile Manipulation through Sliding](https://mlsanity.com/paper/2502.17221/) (2025)
- [Push Smarter, Not Harder: Hierarchical RL-Diffusion Policy for Efficient Nonprehensile Manipulation](https://mlsanity.com/paper/2512.10099/) (2025)
- [ViSA: Visited-State Augmentation for Generalized Goal-Space Contrastive Reinforcement Learning](https://mlsanity.com/paper/2603.14887/) (2026)

## Abstract (arXiv)

Developing robot controllers capable of achieving dexterous nonprehensile manipulation, such as pushing an object on a table, is challenging. The underactuated and hybrid-dynamics nature of the problem, further complicated by the uncertainty resulting from the frictional interactions, requires sophisticated control behaviors. Reinforcement Learning (RL) is a powerful framework for developing such robot controllers. However, previous RL literature addressing the nonprehensile pushing task achieves low accuracy, non-smooth trajectories, and only simple motions, i.e. without rotation of the manipulated object. We conjecture that previously used unimodal exploration strategies fail to capture the inherent hybrid-dynamics of the task, arising from the different possible contact interaction modes between the robot and the object, such as sticking, sliding, and separation. In this work, we propose a multimodal exploration approach through categorical distributions, which enables us to train planar pushing RL policies for arbitrary starting and target object poses, i.e. positions and orientations, and with improved accuracy. We show that the learned policies are robust to external disturbances and observation noise, and scale to tasks with multiple pushers. Furthermore, we validate the transferability of the learned policies, trained entirely in simulation, to a physical robot hardware using the KUKA iiwa robot arm. See our supplemental video: https://youtu.be/vTdva1mgrk4.