paper-with-me

Papers

Model-Based Reinforcement Learning via Imagination with Derived Memory

2021-12-01 · NeurIPS 2021 12 · Yao Mu, Yuzheng Zhuang, Bin Wang, Guangxiang Zhu, Wulong Liu, Jianyu Chen, Ping Luo, Shengbo Li, Chongjie Zhang, Jianye Hao

Model-based reinforcement learning aims to improve the sample efficiency of policy learning by modeling the dynamics of the environment. Recently, the latent dynamics model is further developed to enable fast planning in a compact space. It summarizes the high-dimensional experiences of an agent, which mimics the memory function of humans. Learning policies via imagination with the latent model shows great potential for solving complex tasks. However, only considering memories from the true experiences in the process of imagination could limit its advantages. Inspired by the memory prosthesis proposed by neuroscientists, we present a novel model-based reinforcement learning framework called Imagining with Derived Memory (IDM). It enables the agent to learn policy from enriched diverse imagination with prediction-reliability weight, thus improving sample efficiency and policy robustness. Experiments on various high-dimensional visual control tasks in the DMControl benchmark demonstrate that IDM outperforms previous state-of-the-art methods in terms of policy robustness and further improves the sample efficiency of the model-based method.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Model-based Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Facing Off World Model Backbones: RNNs, Transformers, and S4

2023-07-05 · NeurIPS 2023 11

World models are a fundamental component in model-based reinforcement learning (MBRL). To perform temporally extended and consistent simulations of the future in partially observable environments, world models need to po…

Model-based Reinforcement Learning

Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination

2023-11-11 · Lu Wen, Songan Zhang, H. Eric Tseng, Huei Peng

Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-tr…

Meta Reinforcement Learning

MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models

2026-06-08 · Hao Shi, Weiye Li, Bin Xie, Yulin Wang 외 arxiv

Temporal modeling is essential for robotic manipulation, as effective control requires both memory of past interactions and imagination of future states. However, most VLA models rely primarily on the current observation…

GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control

2026-04-08 · Prakul Sunil Hiremath arxiv

Model-based reinforcement learning (MBRL) improves sample efficiency by optimizing policies inside imagined rollouts, but long-horizon planning degrades when model errors compound and imagined trajectories drift off the …

Computational EfficiencyReinforcement Learning

Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing

2021-03-08 · Axel Brunnbauer, Luigi Berducci, Andreas Brandstätter, Mathias Lechner 외

World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e.g., pixel input…

Autonomous Racingcontinuous-controlContinuous ControlDeep Reinforcement Learning+1