Related papers: ABPT: Amended Backpropagation through Time with Pa…

Random backpropagation (RBP) is a variant of the backpropagation algorithm for training neural networks, where the transpose of the forward matrices are replaced by fixed random matrices in the calculation of the weight updates. It is…

Agile flights of autonomous quadrotors in cluttered environments require constrained motion planning and control subject to translational and rotational dynamics. Traditional model-based methods typically demand complicated design and heavy…

While backpropagation--reverse-mode automatic differentiation--has been extraordinarily successful in deep learning, it requires two passes (forward and backward) through the neural network and the storage of intermediate activations.…

We initiate the study of multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system extending recent results for the special case of stochastic…

In the training of large language models, momentum is widely used and often demonstrated to achieve significant acceleration. However, storing momentum typically presents memory challenges. In this paper, we propose AdaPM, an adaptive…

Offline preference-based reinforcement learning (PbRL) typically operates in two phases: first, use human preferences to learn a reward model and annotate rewards for a reward-free offline dataset; second, learn a policy by optimizing the…

Training recurrent neural networks typically relies on backpropagation through time (BPTT). BPTT depends on forward and backward passes to be completed, rendering the network locked to these computations before loss gradients are available.…

Backpropagation-based approaches aim to align diffusion models with reward functions through end-to-end backpropagation of the reward gradient within the denoising chain, offering a promising perspective. However, due to the computational…

We introduce \`A-la-carte Prompt Tuning (APT), a transformer-based scheme to tune prompts on distinct data so that they can be arbitrarily composed at inference time. The individual prompts can be trained in isolation, possibly on different…

Resource-constrained robotic platforms are particularly useful for tasks that require low-cost hardware alternatives due to the risk of losing the robot, like in search-and-rescue applications, or the need for a large number of devices,…

Data-driven decision-making processes increasingly utilize end-to-end learnable deep neural networks to render final decisions. Sometimes, the output of the forward functions in certain layers is determined by the solutions to mathematical…

Quadrotor flight is an extremely challenging problem due to the limited control authority encountered at the limit of handling. Model Predictive Contouring Control (MPCC) has emerged as a promising model-based approach for time optimization…

Preference-based reinforcement learning (PBRL) offers a promising alternative to explicit reward engineering by learning from pairwise trajectory comparisons. However, real-world preference data often comes from heterogeneous annotators…

Monte Carlo Tree Search (MCTS) methods have proven powerful in planning for sequential decision-making problems such as Go and video games, but their performance can be poor when the planning depth and sampling trajectories are limited or…

We consider the joint design and control of discrete-time stochastic dynamical systems over a finite time horizon. We formulate the problem as a multi-step optimization problem under uncertainty seeking to identify a system design and a…

We propose SwitchTT, a multi-task extension to Trajectory Transformer but enhanced with two striking features: (i) exploiting a sparsely activated model to reduce computation cost in multi-task offline model learning and (ii) adopting a…

Many of the recent advances in the field of artificial intelligence have been fueled by the highly successful backpropagation of error (BP) algorithm, which efficiently solves the credit assignment problem in artificial neural networks.…

In constrained Markov decision processes (CMDPs) with adversarial rewards and constraints, a well-known impossibility result prevents any algorithm from attaining both sublinear regret and sublinear constraint violation, when competing…

Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning. This leaves training susceptible to reward hacking, where models exploit loopholes (e.g.,…

How can one perform Bayesian inference on stochastic simulators with intractable likelihoods? A recent approach is to learn the posterior from adaptively proposed simulations using neural network-based conditional density estimators.…