mlsanityData to 7 Oct 2026

Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivation

arXiv 2102.11051 ↗First posted 22 Feb 2021cs.RO cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

In this paper we address the challenge of exploration in deep reinforcement learning for robotic manipulation tasks. In sparse goal settings, an agent does not receive any positive feedback until randomly achieving the goal, which becomes infeasible for longer control sequences. Inspired by touch-based exploration observed in children, we formulate an intrinsic reward based on the sum of forces between a robot's force sensors and manipulation objects that encourages physical interaction. Furthermore, we introduce contact-prioritized experience replay, a sampling scheme that prioritizes contact rich episodes and transitions. We show that our solution accelerates the exploration and outperforms state-of-the-art methods on three fundamental robot manipulation benchmarks.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 22 of its 32 references that are in the map. First posted on arXiv 22 Feb 2021.

Builds on

22 of 32 references.

References · 22

  1. 2015Continuous control with deep reinforcement learningcited by 3,279
  2. 2016OpenAI Gymcited by 1,684
  3. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  4. 2017Hindsight Experience Replaycited by 1,096
  5. 2015Prioritized Experience Replaycited by 1,070
  6. 2018Exploration by Random Network Distillationcited by 966
  7. 2019Solving Rubik's Cube with a Robot Handcited by 699
  8. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  9. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 632
  10. 2019Learning agile and dynamic motor skills for legged robotscited by 402
  11. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
  12. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 256
10 more
  1. 2019Go-Explore: a New Approach for Hard-Exploration Problemscited by 207
  2. 2019A survey on intrinsic motivation in reinforcement learningcited by 79
  3. 2013Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robotscited by 56
  4. 2019Learning Gentle Object Manipulation with Curiosity-Driven Deep Reinforcement Learningcited by 25
  5. 2018Energy-Based Hindsight Experience Prioritizationcited by 20
  6. 2018Leveraging Contact Forces for Learning to Graspcited by 12
  7. 2019MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learningcited by 11
  8. 2020Learning Functionally Decomposed Hierarchies for Continuous Control Tasks with Path Planningcited by 6
  9. 2020Exploring Exploration: Comparing Children with RL Agents in Unified Environmentscited by 5
  10. 2019How Much Do Unstated Problem Constraints Limit Deep Robotic Reinforcement Learning?cited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 0; 2025: 3; 2026: 1.

7 papers.

  1. 2022DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulationcited by 78
  2. 2025Enhancing Tactile-based Reinforcement Learning for Robotic Controlcited by 5
  3. 2025TwinTac: A Wide-Range, Highly Sensitive Tactile Sensor with Real-to-Sim Digital Twin Sensor Modelcited by 4
  4. 2022SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learningcited by 3
  5. 2023Contact Energy Based Hindsight Experience Prioritizationcited by 1
  6. 2025The Role of Touch: Towards Optimal Tactile Sensing Distribution in Anthropomorphic Hands for Dexterous In-Hand Manipulationcited by 0
  7. 2026Tactile Curiosity Drives Robot Interactioncited by 0