Dynamics-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 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.
Code (2)
Tasks
continuous-controlContinuous Controlreinforcement-learningReinforcement LearningReinforcement Learning (RL)Representation LearningSimilar Papers 제목 키워드 기반
TempoFormer: A Transformer for Temporally-aware Representations in Change Detection
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 LearningNeuron-Aware Active Few-Shot Learning for LLMs
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 LearningMechanistic Insights into Grokking from the Embedding Layer
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
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
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