paper-with-me

홈 › Papers

Dynamics-aware Embeddings

2019-08-25 · ICLR 2020 1 · William Whitney, Rajat Agarwal, Kyunghyun Cho, Abhinav Gupta

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 and action sequences. These embeddings capture the structure of the environment's dynamics, enabling efficient policy learning. We demonstrate that our action embeddings alone improve the sample efficiency and peak performance of model-free RL on control from low-dimensional states. By combining state and action embeddings, we achieve efficient learning of high-quality policies on goal-conditioned continuous control from pixel observations in only 1-2 million environment steps.

📄 PDF Abstract BibTeX arXiv:1908.09357

Code (2)

dyne-submission/dynamics-aware-embeddings 공식 구현 pytorch
willwhitney/dynamics-aware-embeddings pytorch

Tasks

continuous-controlContinuous Controlreinforcement-learningReinforcement LearningReinforcement Learning (RL)Representation Learning

Similar Papers 제목 키워드 기반

TempoFormer: A Transformer for Temporally-aware Representations in Change Detection

2024-08-28 · Talia Tseriotou, Adam Tsakalidis, Maria Liakata

Dynamic representation learning plays a pivotal role in understanding the evolution of linguistic content over time. On this front both context and time dynamics as well as their interplay are of prime importance. Curren…

Change DetectionRepresentation Learning

Neuron-Aware Active Few-Shot Learning for LLMs

2026-07-02 · Zhuowei Chen, Liwei Chen, Christian Schunn, Raquel Coelho 외 arxiv

Active Few-Shot Learning (AFSL) adapts LLMs to specialized domains by identifying the most valuable unlabeled samples for annotation and use as few-shot demonstrations, effectively reducing human annotation costs while p…

Text ClassificationFew-Shot Learning

Mechanistic Insights into Grokking from the Embedding Layer

2025-05-21 · H. V. AlquBoj, Hilal AlQuabeh, Velibor Bojkovic, Munachiso Nwadike 외

Grokking, a delayed generalization in neural networks after perfect training performance, has been observed in Transformers and MLPs, but the components driving it remain underexplored. We show that embeddings are centra…

Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics

2025-08-29 · Sheldon Yu, Yuxin Xiong, Junda Wu, Xintong Li 외 arxiv

Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains limited, with prior work primarily focu…

SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation

2026-04-04 · Guiyu Zhang, Yabo Chen, Xunzhi Xiang, Junchao Huang 외 arxiv

Controlling both camera motion and object dynamics is essential for coherent and expressive video generation, yet current methods typically handle only one motion type or rely on ambiguous 2D cues that entangle camera-in…

Video Generation