Hierarchical safe RL using world-model subgoal generation and imagined rollouts outperforms baselines on long-horizon navigation and manipulation tasks while meeting safety budgets.
Safe reinforcement learning with free-form natural language constraints and pre-trained language models.arXiv preprint arXiv:2401.07553, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Imagine to Ensure Safety in Hierarchical Reinforcement Learning
Hierarchical safe RL using world-model subgoal generation and imagined rollouts outperforms baselines on long-horizon navigation and manipulation tasks while meeting safety budgets.