This section provides basic theoretical details on the log-Sinkhorn operator and its convergence results. Then, we define the functional F(Al): C2(M)/R R, as follows: F(Al) = Z Sl A(x)dµθt(x)+ Z Hϵµ[Sl A](y)dνt(y). The log-Sinkhorn iteration S has the a point in C2(M)/R. This fixed point is determined up to an additive constant, and minimizes the functional F uniformly: F(S Al) F(Al+1) F(Al). Then, the function Al L is approximated to the d2/2-Legendre transformation (11) of the function Bm M. [Al L] If A is a fixed point of the log-Sinkhorn operator S on C2(M)/R, 36th Conference on Neural Information Processing Systems (NeurIPS 2022).

Despite the success of cooperative multi-agent reinforcement learning algorithms, most of them focus on a single team composition, which prevents them from being used in more realistic scenarios where dynamic team composition is possible. While some studies attempt to solve this problem via multi-task learning in a fixed set of team compositions, there is still a risk of overfitting to the training set, which may lead to catastrophic performance when facing dramatically varying team compositions during execution. To address this problem, we propose to use mutual information (MI) as an augmented reward to prevent individual policies from relying too much on team-related information and encourage agents to learn policies that are robust in different team compositions. Optimizing this MI-augmented objective in an off-policy manner can be intractable due to the existence of dynamic marginal distribution. To alleviate this problem, we first propose a multi-agent policy iteration algorithm with a fixed marginal distribution and prove its convergence and optimality. Then, we propose to employ the Blahut-Arimoto algorithm and an imaginary team composition distribution for optimization with approximate marginal distribution as the practical implementation. Empirically, our method demonstrates strong zero-shot generalization to dynamic team compositions in complex cooperative tasks.

We introduce REDO, a class-agnostic framework to REconstruct the Dynamic Objects from RGBD or calibrated videos. Compared to prior work, our problem setting is more realistic yet more challenging for three reasons: 1) due to occlusion or camera settings an object of interest may never be entirely visible, but we aim to reconstruct the complete shape; 2) we aim to handle different object dynamics including rigid motion, non-rigid motion, and articulation; 3) we aim to reconstruct different categories of objects with one unified framework. To address these challenges, we develop two novel modules. First, we introduce a canonical 4D implicit function which is pixel-aligned with aggregated temporal visual cues. Second, we develop a 4D transformation module which captures object dynamics to support temporal propagation and aggregation. We study the efficacy of REDO in extensive experiments on synthetic RGBD video datasets SAIL-VOS 3D and DeformingThings4D++, and on real-world video data 3DPW. We find REDO outperforms state-of-the-art dynamic reconstruction methods by a margin. In ablation studies we validate each developed component.

In order to convert the dataset to NER format we suggest tokenizing Tweet text and utilizing the character offsets to identify mention tokens. E.g. just setting up my twttrwith offsets 19and 24, and DBpedia category as Organization, can be converted to the NERBIO format as follows: tokens, starts, ends = tokenize_with_offsets("just setting up my twttr")and then assigning Olabels to all tokens outside the phrase start and end offsets and B-ORG and I-ORG label to all tokens within the phrase offsets. This approach works as long as the tokenizer returned offsets correspond to the offset of the phrase in the original text, i.e. tokenization is non-destructive. See example code in listing 1. A system span must match a gold span exactly to be counted as correct.

We show that Deep Neural Networks introduce two heteroscedastic Gumbel noise sources into Q-Learning. To account for these noise sources, we propose Double Gumbel Q-Learning, a Deep Q-Learning algorithm applicable for both discrete and continuous control. In discrete control, we derive a closed-form expression for the loss function of our algorithm. In continuous control, this loss function is intractable and we therefore derive an approximation with a hyperparameter whose value regulates pessimism in Q-Learning. We present a default value for our pessimism hyperparameter that enables DoubleGum to outperform DDPG, TD3, SAC, XQL, quantile regression, and Mixture-of-Gaussian Critics in aggregate over 33 tasks from DeepMind Control, MuJoCo, MetaWorld, and Box2D and show that tuning this hyperparameter may further improve sample efficiency.