홈 › Papers

DARLA: Improving Zero-Shot Transfer in Reinforcement Learning

2017-07-26 · ICML 2017 8 · Irina Higgins, Arka Pal, Andrei A. Rusu, Loic Matthey, Christopher P. Burgess, Alexander Pritzel, Matthew Botvinick, Charles Blundell, Alexander Lerchner

Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act. DARLA's vision is based on learning a disentangled representation of the observed environment. Once DARLA can see, it is able to acquire source policies that are robust to many domain shifts - even with no access to the target domain. DARLA significantly outperforms conventional baselines in zero-shot domain adaptation scenarios, an effect that holds across a variety of RL environments (Jaco arm, DeepMind Lab) and base RL algorithms (DQN, A3C and EC).

📄 PDF Abstract BibTeX arXiv:1707.08475

Code (1)

BCHoagland/DARLA pytorch

Tasks

Deep Reinforcement LearningDomain Adaptation reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Representation Learning

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

A3C A3C, Asynchronous Advantage Actor Critic, is a policy gradient algorithm in reinforcement learning that maintains a policy $\pi\left(a\_{t}\mid{s}\_{t}; \theta\right)$ and…

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer

2024-04-08 · Xinyang Gu, Yen-Jen Wang, Jianyu Chen

Humanoid-Gym is an easy-to-use reinforcement learning (RL) framework based on Nvidia Isaac Gym, designed to train locomotion skills for humanoid robots, emphasizing zero-shot transfer from simulation to the real-world en…

MuJoCo Physical Simulations Reinforcement Learning (RL)

Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning

2018-12-01 · NeurIPS 2018 12 · Ofir Marom, Benjamin Rosman

Object-oriented representations in reinforcement learning have shown promise in transfer learning, with previous research introducing a propositional object-oriented framework that has provably efficient learning bounds …

Object reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+2

Zero-Shot Reinforcement Learning via Function Encoders

2024-01-30 · Tyler Ingebrand, Amy Zhang, Ufuk Topcu

Although reinforcement learning (RL) can solve many challenging sequential decision making problems, achieving zero-shot transfer across related tasks remains a challenge. The difficulty lies in finding a good representa…

Decision Making reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+2

Difference-Based Relational Learning for Zero-Shot Object-Goal Visual Navigation With Direct Sim-to-Real Transfer

2026-07-17 · Guolei Qi, Feitian Zhang arxiv

End-to-end deep reinforcement learning (DRL) for zero-shot object-goal visual navigation remains challenged by the sim-to-real gap, particularly variations in object appearance and restricted camera field-of-view (FoV). …

Zero-shot Generalization Reinforcement Learning Visual Navigation

Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems

2022-04-27 · Rushang Karia, Siddharth Srivastava

Reinforcement learning in problems with symbolic state spaces is challenging due to the need for reasoning over long horizons. This paper presents a new approach that utilizes relational abstractions in conjunction with …

Object reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)