# Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain

arXiv: https://arxiv.org/abs/1510.02879 · HTML: https://mlsanity.com/paper/1510.02879/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2015.

## Built on by (most cited first, 19 of 19)

- [Modular Deep Learning](https://mlsanity.com/paper/2302.11529/) (2023)
- [Combining Modular Skills in Multitask Learning](https://mlsanity.com/paper/2202.13914/) (2022)
- [Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning](https://mlsanity.com/paper/2310.03718/) (2023)
- [Conditional computation in neural networks: principles and research trends](https://mlsanity.com/paper/2403.07965/) (2024)
- [Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning](https://mlsanity.com/paper/2312.03248/) (2023)
- [Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning](https://mlsanity.com/paper/2210.03729/) (2022)
- [Learning Label Modular Prompts for Text Classification in the Wild](https://mlsanity.com/paper/2211.17142/) (2022)
- [Safety-Constrained Policy Transfer with Successor Features](https://mlsanity.com/paper/2211.05361/) (2022)
- [Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery](https://mlsanity.com/paper/2311.14270/) (2023)
- [Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts](https://mlsanity.com/paper/2003.00203/) (2020)
- [Malleable Agents for Re-Configurable Robotic Manipulators](https://mlsanity.com/paper/2202.02395/) (2022)
- [Fusing Interpretable Knowledge of Neural Network Learning Agents For Swarm-Guidance](https://mlsanity.com/paper/2204.00272/) (2022)
- [Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2206.05750/) (2022)
- [Adaptive Aggregation for Safety-Critical Control](https://mlsanity.com/paper/2302.03586/) (2023)
- [Shared learning of powertrain control policies for vehicle fleets](https://mlsanity.com/paper/2404.17892/) (2024)
- [Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains](https://mlsanity.com/paper/2507.03026/) (2025)
- [Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning](https://mlsanity.com/paper/2603.00903/) (2026)
- [ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2606.24601/) (2026)
- [Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation](https://mlsanity.com/paper/2610.00729/) (2026)

## Abstract (arXiv)

Transferring knowledge from prior source tasks in solving a new target task can be useful in several learning applications. The application of transfer poses two serious challenges which have not been adequately addressed. First, the agent should be able to avoid negative transfer, which happens when the transfer hampers or slows down the learning instead of helping it. Second, the agent should be able to selectively transfer, which is the ability to select and transfer from different and multiple source tasks for different parts of the state space of the target task. We propose A2T (Attend, Adapt and Transfer), an attentive deep architecture which adapts and transfers from these source tasks. Our model is generic enough to effect transfer of either policies or value functions. Empirical evaluations on different learning algorithms show that A2T is an effective architecture for transfer by being able to avoid negative transfer while transferring selectively from multiple source tasks in the same domain.