Gridworld
PulseAugur coverage of Gridworld — every cluster mentioning Gridworld across labs, papers, and developer communities, ranked by signal.
-
New framework optimizes multi-robot exploration under budget constraints
Researchers have developed a new distributed semantic exploration framework for multi-robot systems that addresses communication and mobility constraints. The framework integrates Dirichlet mapping, budget-constrained t…
-
New L-ICL technique enhances LLM planning accuracy
Researchers have developed a new technique called Localized In-Context Learning (L-ICL) to improve the planning capabilities of large language models (LLMs). This method involves iteratively augmenting instructions with…
-
New sub-quadratic method improves bisimulation metric computation for MDPs
Researchers have developed a novel sub-quadratic method for calculating bisimulation metrics in Markov decision processes (MDPs). This new approach utilizes approximate nearest neighbor (ANN) indexing to efficiently sel…
-
Q-learning integration boosts offline In-Context RL performance
A new research paper explores the effectiveness of integrating Reinforcement Learning (RL) objectives into offline In-Context Reinforcement Learning (ICRL) methods. Experiments across over 150 datasets in GridWorld and …