# Learning Vision-based Robotic Manipulation Tasks Sequentially in Offline Reinforcement Learning Settings

arXiv: https://arxiv.org/abs/2301.13450 · HTML: https://mlsanity.com/paper/2301.13450/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Real-world robot offline RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 25 of its 44 references that are in the map.
- First posted on arXiv 31 Jan 2023.

## Placed in

- Offline RL and imitation learning from data / [Real-world robot offline RL](https://mlsanity.com/offlinerl/real-world-robot-offline-rl/)

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [Distral: Robust Multitask Reinforcement Learning](https://mlsanity.com/paper/1707.04175/) (2017)
- [Multi-Task Reinforcement Learning with Context-based Representations](https://mlsanity.com/paper/2102.06177/) (2021)
- [Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer](https://mlsanity.com/paper/1609.07088/) (2016)
- [Continual World: A Robotic Benchmark For Continual Reinforcement Learning](https://mlsanity.com/paper/2105.10919/) (2021)
- [Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention](https://mlsanity.com/paper/2104.11203/) (2021)
- [Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation](https://mlsanity.com/paper/1703.02018/) (2017)
- [COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning](https://mlsanity.com/paper/2010.14500/) (2020)
- [Composable Deep Reinforcement Learning for Robotic Manipulation](https://mlsanity.com/paper/1803.06773/) (2018)
- [Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards](https://mlsanity.com/paper/1906.05841/) (2019)
- [Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience](https://mlsanity.com/paper/2010.03209/) (2020)
- [Self-supervised Learning for Precise Pick-and-place without Object Model](https://mlsanity.com/paper/2006.08373/) (2020)

## Built on by (most cited first, 2 of 2)

- [TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models](https://mlsanity.com/paper/2511.05275/) (2025)
- [CIDER: Continual Interactive Distillation for Embodied Reinforcement Learning](https://mlsanity.com/paper/2608.21899/) (2026)

## Abstract (arXiv)

With the rise of deep reinforcement learning (RL) methods, many complex robotic manipulation tasks are being solved. However, harnessing the full power of deep learning requires large datasets. Online-RL does not suit itself readily into this paradigm due to costly and time-taking agent environment interaction. Therefore recently, many offline-RL algorithms have been proposed to learn robotic tasks. But mainly, all such methods focus on a single task or multi-task learning, which requires retraining every time we need to learn a new task. Continuously learning tasks without forgetting previous knowledge combined with the power of offline deep-RL would allow us to scale the number of tasks by keep adding them one-after-another. In this paper, we investigate the effectiveness of regularisation-based methods like synaptic intelligence for sequentially learning image-based robotic manipulation tasks in an offline-RL setup. We evaluate the performance of this combined framework against common challenges of sequential learning: catastrophic forgetting and forward knowledge transfer. We performed experiments with different task combinations to analyze the effect of task ordering. We also investigated the effect of the number of object configurations and density of robot trajectories. We found that learning tasks sequentially helps in the propagation of knowledge from previous tasks, thereby reducing the time required to learn a new task. Regularisation based approaches for continuous learning like the synaptic intelligence method although helps in mitigating catastrophic forgetting but has shown only limited transfer of knowledge from previous tasks.