paper-with-me

Papers

Task-Agnostic Dynamics Priors for Deep Reinforcement Learning

2019-05-13 · Yilun Du, Karthik Narasimhan

While model-based deep reinforcement learning (RL) holds great promise for sample efficiency and generalization, learning an accurate dynamics model is often challenging and requires substantial interaction with the environment. A wide variety of domains have dynamics that share common foundations like the laws of classical mechanics, which are rarely exploited by existing algorithms. In fact, humans continuously acquire and use such dynamics priors to easily adapt to operating in new environments. In this work, we propose an approach to learn task-agnostic dynamics priors from videos and incorporate them into an RL agent. Our method involves pre-training a frame predictor on task-agnostic physics videos to initialize dynamics models (and fine-tune them) for unseen target environments. Our frame prediction architecture, SpatialNet, is designed specifically to capture localized physical phenomena and interactions. Our approach allows for both faster policy learning and convergence to better policies, outperforming competitive approaches on several different environments. We also demonstrate that incorporating this prior allows for more effective transfer between environments.

📄 PDF Abstract BibTeX arXiv:1905.04819

Code (1)

yilundu/task_agnostic_dynamics_prior 공식 구현 tf

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization

2019-10-17 · NASA ADS 2019 10 · Huazhe Xu *1, Boyuan Chen *1, Yang Gao1, and Trevor Darrell1

Abstract Humans can learn task-agnostic priors from interactive experience and utilize the priors for novel tasks without any finetuning. In this paper, we propose Scoring-Aggregating-Planning (SAP), a framework that ca…

Zero-shot Generalization

Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization

2019-09-25 · Huazhe Xu, Boyuan Chen, Yang Gao, Trevor Darrell

Humans can learn task-agnostic priors from interactive experience and utilize the priors for novel tasks without any finetuning. In this paper, we propose Scoring-Aggregating-Planning (SAP), a framework that can learn ta…

Zero-shot Generalization

Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations

2024-12-02 · Cevahir Koprulu, Po-han Li, Tianyu Qiu, Ruihan Zhao 외

Many continuous control problems can be formulated as sparse-reward reinforcement learning (RL) tasks. In principle, online RL methods can automatically explore the state space to solve each new task. However, discoverin…

continuous-controlContinuous ControlReinforcement Learning (RL)

Learning Physics Priors for Deep Reinforcement Learing

2018-09-27 · Yilun Du, Karthik Narasimhan

While model-based deep reinforcement learning (RL) holds great promise for sample efficiency and generalization, learning an accurate dynamics model is challenging and often requires substantial interactions with the env…

Deep Reinforcement LearningReinforcement Learning (RL)Transfer Learning

CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations

2022-10-18 · Kai Yan, Alexander G. Schwing, Yu-Xiong Wang

Although reinforcement learning has found widespread use in dense reward settings, training autonomous agents with sparse rewards remains challenging. To address this difficulty, prior work has shown promising results wh…

Formreinforcement-learningReinforcement Learning (RL)Retrieval