Data to 7 Oct 2026

Sim-to-Real Robot Learning from Pixels with Progressive Nets

arXiv 1610.04286 ↗First posted 13 Oct 2016cs.RO cs.LGcited by 89

Not on the map. Why?

Abstract (arXiv)

Applying end-to-end learning to solve complex, interactive, pixel-driven control tasks on a robot is an unsolved problem. Deep Reinforcement Learning algorithms are too slow to achieve performance on a real robot, but their potential has been demonstrated in simulated environments. We propose using progressive networks to bridge the reality gap and transfer learned policies from simulation to the real world. The progressive net approach is a general framework that enables reuse of everything from low-level visual features to high-level policies for transfer to new tasks, enabling a compositional, yet simple, approach to building complex skills. We present an early demonstration of this approach with a number of experiments in the domain of robot manipulation that focus on bridging the reality gap. Unlike other proposed approaches, our real-world experiments demonstrate successful task learning from raw visual input on a fully actuated robot manipulator. Moreover, rather than relying on model-based trajectory optimisation, the task learning is accomplished using only deep reinforcement learning and sparse rewards.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Oct 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 0; 2021: 29; 2022: 19; 2023: 14; 2024: 10; 2025: 10; 2026: 5.

89 papers.

Sort:

By area:

2023Learning Interactive Real-World Simulatorscited by 440
2022DayDreamer: World Models for Physical Robot Learningcited by 372
2021PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingcited by 298
2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
2024Video as the New Language for Real-World Decision Makingcited by 86
2021Asymmetric self-play for automatic goal discovery in robotic manipulationcited by 71
2021Understanding Domain Randomization for Sim-to-real Transfercited by 69
2022A Survey on Model-based Reinforcement Learningcited by 65
2021Robot Learning from Randomized Simulations: A Reviewcited by 56
2021Learning to See before Learning to Act: Visual Pre-training for Manipulationcited by 50
2023Polybot: Training One Policy Across Robots While Embracing Variabilitycited by 28
2023MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulationcited by 27

38 more

2021Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systemscited by 24
2022Investigating the Properties of Neural Network Representations in Reinforcement Learningcited by 24
2025The Reality Gap in Robotics: Challenges, Solutions, and Best Practicescited by 22
2022Dungeons and Data: A Large-Scale NetHack Datasetcited by 16
2022A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learningcited by 15
2023AdaptNet: Policy Adaptation for Physics-Based Character Controlcited by 15
2021Can Q-Learning be Improved with Advice?cited by 13
2021Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Groundingcited by 12
2021The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agentscited by 12
2021Deep Network Approximation in Terms of Intrinsic Parameterscited by 12
2022Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Taskscited by 12
2021REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Cluttercited by 11
2022Generalization in Neural Networks: A Broad Surveycited by 11
2025Self-Composing Policies for Scalable Continual Reinforcement Learningcited by 10
2021LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Sparse Reward Iterative Taskscited by 9
2022Provable Sim-to-real Transfer in Continuous Domain with Partial Observationscited by 9
2023Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrationscited by 8
2022Explaining Reinforcement Learning Policies through Counterfactual Trajectoriescited by 7
2022On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardnesscited by 7
2023Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomycited by 6
2023Continual Learning of Unsupervised Monocular Depth from Videoscited by 5
2021Q-Value Weighted Regression: Reinforcement Learning with Limited Datacited by 4
2022Policy Learning for Robust Markov Decision Process with a Mismatched Generative Modelcited by 4
2022CtrlFormer: Learning Transferable State Representation for Visual Control via Transformercited by 4
2022Probing Transfer in Deep Reinforcement Learning without Task Engineeringcited by 4
2023Evaluating Continual Learning on a Home Robotcited by 4
2023DiAReL: Reinforcement Learning with Disturbance Awareness for Robust Sim2Real Policy Transfer in Robot Controlcited by 4
2023Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networkscited by 4
2024Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimizationcited by 4
2024Simulation-Aided Policy Tuning for Black-Box Robot Learningcited by 4
2025Adversarial Diffusion for Robust Reinforcement Learningcited by 4
2021A Bayesian Approach to Reinforcement Learning of Vision-Based Vehicular Controlcited by 3
2021Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robotscited by 3
2021ARC: Adversarially Robust Control Policies for Autonomous Vehiclescited by 3
2021SIM2REALVIZ: Visualizing the Sim2Real Gap in Robot Ego-Pose Estimationcited by 3
2024Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Modelcited by 3
2021Pre-training of Deep RL Agents for Improved Learning under Domain Randomizationcited by 2
2021Pretrained Encoders are All You Needcited by 2

50 most cited of 89 All 89 (JSON)