This is a major hindrance to the practical implementation of many proposed solutions.

In Section B, we summarize the statistics of the dataset. A.1 ObjectSpace Recall that HandMeThat uses an object-centric representation for states. Object hierarchy.HandMeThat classifies all categories into 5classes: location, receptacle, food, tool,andthing. Each class (except for"location") iscomposed ofmultiple subclasses, and each subclass contains several object categories. Intotal, there are155 object categories.

While previousbenchmarks insimilar domains havebeenprimarily focusing onthelanguage grounding of object properties (e.g., "table"), relations (e.g., "on"), and planning (e.g., object search and manipulation) [6,7],inthispaper,wehighlights theadditional challenge forunderstanding human instructions withambiguities (i.e., recognizing the subgoal) based on physical states and human actionsandgoals. Each episode in HandMeThat contains twostages.

Training recurrent neural networks (RNNs) remains a challenge due to the instability of gradients across long time horizons, which can lead to exploding and vanishing gradients. Recent research has linked these problems to the values of Lyapunov exponents for the forward-dynamics, which describe the growth or shrinkage of infinitesimal perturbations. Here, we propose gradient flossing, a novel approach to tackling gradient instability by pushing Lyapunov exponents of the forward dynamics toward zero during learning.

Training recurrent neural networks (RNNs) remains a challenge due to the instability of gradients across long time horizons, which can lead to exploding and vanishing gradients. Recent research has linked these problems to the values of Lyapunov exponents for the forward-dynamics, which describe the growth or shrinkage of infinitesimal perturbations. Here, we propose gradient flossing, a novel approach to tackling gradient instability by pushing Lyapunov exponents of the forward dynamics toward zero during learning.

If Conditions 1 and 3 hold, andthemargin isnon-zero, datacollectedinbatchesusing -greedy, Thompson Sampling, or UCBwithclipping constraintwithf(n)= c forsome0