paper-with-me

홈 › Papers

A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning

2021-06-03 · NeurIPS 2021 12 · Mingde Zhao, Zhen Liu, Sitao Luan, Shuyuan Zhang, Doina Precup, Yoshua Bengio

We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning. The agent uses a bottleneck mechanism over a set-based representation to force the number of entities to which the agent attends at each planning step to be small. In experiments, we investigate the bottleneck mechanism with several sets of customized environments featuring different challenges. We consistently observe that the design allows the planning agents to generalize their learned task-solving abilities in compatible unseen environments by attending to the relevant objects, leading to better out-of-distribution generalization performance.

📄 PDF Abstract BibTeX arXiv:2106.02097

Code (1)

mila-iqia/conscious-planning 공식 구현 tf

Tasks

Deep Reinforcement LearningModel-based Reinforcement LearningOut-of-Distribution Generalizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning

2023-09-30 · Mingde Zhao, Safa Alver, Harm van Seijen, Romain Laroche 외

Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning framework utilizing spatio-temporal abstractions to generalize better in novel situations. It automatically decomposes the gi…

Decision MakingModel-based Reinforcement Learningreinforcement-learningZero-shot Generalization

Probing for Consciousness in Machines

2024-11-25 · Mathis Immertreu, Achim Schilling, Andreas Maier, Patrick Krauss

This study explores the potential for artificial agents to develop core consciousness, as proposed by Antonio Damasio's theory of consciousness. According to Damasio, the emergence of core consciousness relies on the int…

Reinforcement Learning (RL)

CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness

2026-04-30 · Haofei Yu, Yining Zhao, Lenore Blum, Manuel Blum 외 arxiv

Despite remarkable advances, today's AI systems remain narrow in scope, falling short of the flexible, adaptive, and multisensory intelligence that characterizes human capabilities. This gap has fueled longstanding debat…

Emergent Language as an Approach to Conscious AI

2026-06-04 · Zengqing Wu, Chuan Xiao arxiv

The question of whether artificial systems can be conscious remains open, in part because existing approaches either evaluate systems against theory-derived checklists (discriminative) or engineer consciousness-inspired …

Multi-agent Reinforcement Learning

Brain-Inspired Planning for Better Generalization in Reinforcement Learning

2025-11-09 · Mingde "Harry" Zhao arxiv

Existing Reinforcement Learning (RL) systems encounter significant challenges when applied to real-world scenarios, primarily due to poor generalization across environments that differ from their training conditions. Thi…

Reinforcement Learning