# COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning

arXiv: https://arxiv.org/abs/2010.14500 · HTML: https://mlsanity.com/paper/2010.14500/

## Key facts

- Cited by 83 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 34 of its 51 references that are in the map.
- First posted on arXiv 27 Oct 2020.

## 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, 30 of 34)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection](https://mlsanity.com/paper/1603.02199/) (2016)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog](https://mlsanity.com/paper/1907.00456/) (2019)
- [Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control](https://mlsanity.com/paper/1812.00568/) (2018)
- [Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours](https://mlsanity.com/paper/1509.06825/) (2015)
- [Search on the Replay Buffer: Bridging Planning and Reinforcement Learning](https://mlsanity.com/paper/1906.05253/) (2019)
- [Sim-to-Real Reinforcement Learning for Deformable Object Manipulation](https://mlsanity.com/paper/1806.07851/) (2018)
- [Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning](https://mlsanity.com/paper/1803.09956/) (2018)
- [End-to-End Robotic Reinforcement Learning without Reward Engineering](https://mlsanity.com/paper/1904.07854/) (2019)
- [Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations](https://mlsanity.com/paper/2003.06085/) (2020)
- [IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data](https://mlsanity.com/paper/1911.05321/) (2019)
- [Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation](https://mlsanity.com/paper/1909.05829/) (2019)
- [Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias](https://mlsanity.com/paper/1807.07049/) (2018)
- [Diagnosing Bottlenecks in Deep Q-learning Algorithms](https://mlsanity.com/paper/1902.10250/) (2019)
- [Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight](https://mlsanity.com/paper/1904.05538/) (2019)
- [Learning Dexterous Manipulation Policies from Experience and Imitation](https://mlsanity.com/paper/1611.05095/) (2016)
- [Visual Closed-Loop Control for Pouring Liquids](https://mlsanity.com/paper/1610.02610/) (2016)
- [Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search](https://mlsanity.com/paper/1610.00673/) (2016)

## Built on by (most cited first, 30 of 83)

- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [COMBO: Conservative Offline Model-Based Policy Optimization](https://mlsanity.com/paper/2102.08363/) (2021)
- [Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning](https://mlsanity.com/paper/2303.05479/) (2023)
- [A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems](https://mlsanity.com/paper/2203.01387/) (2022)
- [Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble](https://mlsanity.com/paper/2107.00591/) (2021)
- [Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills](https://mlsanity.com/paper/2104.07749/) (2021)
- [RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2204.12581/) (2022)
- [Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment](https://mlsanity.com/paper/2211.08416/) (2022)
- [When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?](https://mlsanity.com/paper/2204.05618/) (2022)
- [S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning](https://mlsanity.com/paper/2103.06326/) (2021)
- [Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials](https://mlsanity.com/paper/2210.05178/) (2022)
- [Learning and Retrieval from Prior Data for Skill-based Imitation Learning](https://mlsanity.com/paper/2210.11435/) (2022)
- [Demonstration-Guided Reinforcement Learning with Learned Skills](https://mlsanity.com/paper/2107.10253/) (2021)
- [A Workflow for Offline Model-Free Robotic Reinforcement Learning](https://mlsanity.com/paper/2109.10813/) (2021)
- [DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization](https://mlsanity.com/paper/2112.04716/) (2021)
- [Conservative Data Sharing for Multi-Task Offline Reinforcement Learning](https://mlsanity.com/paper/2109.08128/) (2021)
- [How to Leverage Unlabeled Data in Offline Reinforcement Learning](https://mlsanity.com/paper/2202.01741/) (2022)
- [Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning](https://mlsanity.com/paper/2205.11790/) (2022)
- [Offline Reinforcement Learning with Reverse Model-based Imagination](https://mlsanity.com/paper/2110.00188/) (2021)
- [Chat with the Environment: Interactive Multimodal Perception Using Large Language Models](https://mlsanity.com/paper/2303.08268/) (2023)
- [Offline Meta-Reinforcement Learning for Industrial Insertion](https://mlsanity.com/paper/2110.04276/) (2021)
- [Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2210.13846/) (2022)
- [Robotic Offline RL from Internet Videos via Value-Function Pre-Training](https://mlsanity.com/paper/2309.13041/) (2023)
- [Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space](https://mlsanity.com/paper/2205.08129/) (2022)
- [Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study](https://mlsanity.com/paper/2103.11512/) (2021)
- [Offline Reinforcement Learning for Visual Navigation](https://mlsanity.com/paper/2212.08244/) (2022)
- [Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks](https://mlsanity.com/paper/2210.06601/) (2022)
- [SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling](https://mlsanity.com/paper/2306.11886/) (2023)
- [Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination](https://mlsanity.com/paper/2206.07989/) (2022)
- [Accelerating Exploration with Unlabeled Prior Data](https://mlsanity.com/paper/2311.05067/) (2023)

## Abstract (arXiv)

Reinforcement learning has been applied to a wide variety of robotics problems, but most of such applications involve collecting data from scratch for each new task. Since the amount of robot data we can collect for any single task is limited by time and cost considerations, the learned behavior is typically narrow: the policy can only execute the task in a handful of scenarios that it was trained on. What if there was a way to incorporate a large amount of prior data, either from previously solved tasks or from unsupervised or undirected environment interaction, to extend and generalize learned behaviors? While most prior work on extending robotic skills using pre-collected data focuses on building explicit hierarchies or skill decompositions, we show in this paper that we can reuse prior data to extend new skills simply through dynamic programming. We show that even when the prior data does not actually succeed at solving the new task, it can still be utilized for learning a better policy, by providing the agent with a broader understanding of the mechanics of its environment. We demonstrate the effectiveness of our approach by chaining together several behaviors seen in prior datasets for solving a new task, with our hardest experimental setting involving composing four robotic skills in a row: picking, placing, drawer opening, and grasping, where a +1/0 sparse reward is provided only on task completion. We train our policies in an end-to-end fashion, mapping high-dimensional image observations to low-level robot control commands, and present results in both simulated and real world domains. Additional materials and source code can be found on our project website: https://sites.google.com/view/cog-rl