Data to 7 Oct 2026

Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning

arXiv 1511.06342 ↗First posted 19 Nov 2015cs.LGcited by 176

Not on the map. Why?

Abstract (arXiv)

The ability to act in multiple environments and transfer previous knowledge to new situations can be considered a critical aspect of any intelligent agent. Towards this goal, we define a novel method of multitask and transfer learning that enables an autonomous agent to learn how to behave in multiple tasks simultaneously, and then generalize its knowledge to new domains. This method, termed "Actor-Mimic", exploits the use of deep reinforcement learning and model compression techniques to train a single policy network that learns how to act in a set of distinct tasks by using the guidance of several expert teachers. We then show that the representations learnt by the deep policy network are capable of generalizing to new tasks with no prior expert guidance, speeding up learning in novel environments. Although our method can in general be applied to a wide range of problems, we use Atari games as a testing environment to demonstrate these methods.

Key facts. Cited by 176 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Nov 2015.

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: 1; 2021: 43; 2022: 43; 2023: 28; 2024: 22; 2025: 22; 2026: 15.

176 papers.

Sort:

By area:

2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
2023On-Policy Distillation of Language Models: Learning from Self-Generated Mistakescited by 840
2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 441
2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 226
2022Multi-Game Decision Transformerscited by 212
2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 201
2021Multi-Task Reinforcement Learning with Context-based Representationscited by 169
2024Yell At Your Robot: Improving On-the-Fly from Language Correctionscited by 123
2021Rapid Exploration for Open-World Navigation with Latent Goal Modelscited by 118
2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 111
2022M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-designcited by 97

38 more

2021Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Interventioncited by 90
2022Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trialscited by 78
2022Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizescited by 72
2023Independent Component Alignment for Multi-Task Learningcited by 69
2022In Defense of the Unitary Scalarization for Deep Multi-Task Learningcited by 65
2021Conservative Data Sharing for Multi-Task Offline Reinforcement Learningcited by 64
2022Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progresscited by 63
2021Robot Learning from Randomized Simulations: A Reviewcited by 56
2023Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learningcited by 50
2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
2021A Survey on Ensemble Learning under the Era of Deep Learningcited by 47
2021Near-optimal Representation Learning for Linear Bandits and Linear RLcited by 45
2024Sharing Knowledge in Multi-Task Deep Reinforcement Learningcited by 42
2021Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challengescited by 40
2021UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformerscited by 39
2022Hypernetworks in Meta-Reinforcement Learningcited by 39
2022Provable Benefits of Representational Transfer in Reinforcement Learningcited by 38
2021Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agentscited by 35
2021Efficient Transformers in Reinforcement Learning using Actor-Learner Distillationcited by 35
2022On Transforming Reinforcement Learning by Transformer: The Development Trajectorycited by 35
2021Lifelong Robotic Reinforcement Learning by Retaining Experiencescited by 34
2021On the Power of Multitask Representation Learning in Linear MDPcited by 30
2023Cross-Domain Policy Adaptation via Value-Guided Data Filteringcited by 30
2021Universal Trading for Order Execution with Oracle Policy Distillationcited by 29
2021Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillationcited by 28
2022Improving Multi-Task Generalization via Regularizing Spurious Correlationcited by 28
2022Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learningcited by 28
2023Polybot: Training One Policy Across Robots While Embracing Variabilitycited by 28
2022Towards Versatile Embodied Navigationcited by 26
2022AnyMorph: Learning Transferable Polices By Inferring Agent Morphologycited by 25
2024Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problemcited by 23
2025Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learnerscited by 23
2023Causal Reinforcement Learning: A Surveycited by 22
2024Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agentcited by 20
2021When Is Generalizable Reinforcement Learning Tractable?cited by 19
2021Domain Adversarial Reinforcement Learningcited by 19
2021Sequoia: A Software Framework to Unify Continual Learning Researchcited by 19
2022Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Taskscited by 17

50 most cited of 176 All 176 (JSON)