Self-supervised Learning of Image Embedding for Continuous Control
Operating directly from raw high dimensional sensory inputs like images is still a challenge for robotic control. Recently, Reinforcement Learning methods have been proposed to solve specific tasks end-to-end, from pixels to torques. However, these approaches assume the access to a specified reward which may require specialized instrumentation of the environment. Furthermore, the obtained policy and representations tend to be task specific and may not transfer well. In this work we investigate completely self-supervised learning of a general image embedding and control primitives, based on finding the shortest time to reach any state. We also introduce a new structure for the state-action value function that builds a connection between model-free and model-based methods, and improves the performance of the learning algorithm. We experimentally demonstrate these findings in three simulated robotic tasks.
Code (1)
Tasks
continuous-controlContinuous ControlReinforcement LearningSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Self-Supervised Learning as Discrete Communication
Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensi…
Self-Supervised LearningImage ClassificationDynamics-aware Embeddings
In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states an…
continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+2Measuring Visual Generalization in Continuous Control from Pixels
Self-supervised learning and data augmentation have significantly reduced the performance gap between state and image-based reinforcement learning agents in continuous control tasks. However, it is still unclear whether …
continuous-controlContinuous ControlData AugmentationReinforcement Learning (RL)+1UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
The Segment Anything Model (SAM) family has become a widely adopted vision foundation model, but its ability to control segmentation granularity remains limited. Users often need to refine results manually - by adding mo…
Self-Supervised LearningContinuous ControlVideo SegmentationSelfie: Self-supervised Pretraining for Image Embedding
We introduce a pretraining technique called Selfie, which stands for SELFie supervised Image Embedding. Selfie generalizes the concept of masked language modeling of BERT (Devlin et al., 2019) to continuous data, such as…
Language ModelingLanguage ModellingMasked Language Modeling