REVIEW 6 cited by
SafeDreamer: Safe Reinforcement Learning with World Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) methods, which rely on cost functions to enforce safety, often fail to achieve zero-cost performance in complex scenarios, especially vision-only tasks. These limitations are primarily due to model inaccuracies and inadequate sample efficiency. The integration of the world model has proven effective in mitigating these shortcomings. In this work, we introduce SafeDreamer, a novel algorithm incorporating Lagrangian-based methods into world model planning processes within the superior Dreamer framework. Our method achieves nearly zero-cost performance on various tasks, spanning low-dimensional and vision-only input, within the Safety-Gymnasium benchmark, showcasing its efficacy in balancing performance and safety in RL tasks. Further details can be found in the code repository: \url{https://github.com/PKU-Alignment/SafeDreamer}.
Forward citations
Cited by 6 Pith papers
-
Latent Chain-of-Thought World Modeling for End-to-End Driving
LCDrive unifies chain-of-thought reasoning and action selection for end-to-end driving by interleaving action-proposal tokens and latent world-model tokens that predict action outcomes, yielding faster inference and b...
-
Human Cognition in Machines: A Unified Perspective of World Models
The paper introduces a unified framework for world models that fully incorporates all cognitive functions from Cognitive Architecture Theory, highlights under-researched areas in motivation and meta-cognition, and pro...
-
Safety, Security, and Cognitive Risks in World Models
World models enable efficient AI planning but create risks from adversarial corruption, goal misgeneralization, and human bias, demonstrated via attacks that amplify errors and reduce rewards on models like RSSM and D...
-
Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control
Proposes hierarchical MARL framework enforcing safety via constraint manifold at low level with theoretical guarantees and stationary dynamics for stable training and generalization.
-
SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration
SHAPO adds a sharpness-aware adjustment to policy optimization that reweights gradients to favor conservative behavior in uncertain areas, yielding better safety-performance tradeoffs on continuous control tasks.
-
Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges
A survey reviewing how world models and agentic AI could be combined to give edge devices predictive, proactive decision-making, with a taxonomy of methods, applications, and challenges.
Discussion (0). Sign in to comment.