Stochastic gradient descent (SGD) is the main algorithm behind a large body of work in machine learning. In many cases, constraints are enforced via projections, leading to projected stochastic gradient algorithms. In recent years, a large body of work has examined the convergence properties of projected SGD for non-convex losses in asymptotic and non-asymptotic settings. Strong quantitative guarantees are available for convergence measured via Moreau envelopes. However, these results cannot be compared directly with work on unconstrained SGD, since the Moreau envelope construction changes the gradient. Other common measures based on gradient mappings have the limitation that convergence can only be guaranteed if variance reduction methods, such as mini-batching, are employed. This paper presents an analysis of projected SGD for non-convex losses over compact convex sets. Convergence is measured via the distance of the gradient to the Goldstein subdifferential generated by the constraints. Our proposed convergence criterion directly reduces to commonly used criteria in the unconstrained case, and we obtain convergence without requiring variance reduction. We obtain results for data that are independent, identically distributed (IID) or satisfy mixing conditions ($L$-mixing). In these cases, we derive asymptotic convergence and $O(N^{-1/3})$ non-asymptotic bounds in expectation, where $N$ is the number of steps. In the case of IID sub-Gaussian data, we obtain almost-sure asymptotic convergence and high-probability non-asymptotic $O(N^{-1/5})$ bounds. In particular, these are the first non-asymptotic high-probability bounds for projected SGD with non-convex losses.

Reinforcement learning (RL) techniques have achieved impressive performance on simulated benchmarks such as Atari100k, yet recent advances remain largely confined to simulation and show limited transfer to real-world domains. A central obstacle is environmental stochasticity, as real systems involve noisy observations, unpredictable dynamics, and non-stationary conditions that undermine the stability of current methods. Existing benchmarks rarely capture these uncertainties and favor simplified settings where algorithms can be tuned to succeed. The absence of a well-defined taxonomy of stochasticity further complicates evaluation, as robustness to one type of stochastic perturbation, such as sticky actions, does not guarantee robustness to other forms of uncertainty. To address this critical gap, we introduce STORI (STOchastic-ataRI), a benchmark that systematically incorporates diverse stochastic effects and enables rigorous evaluation of RL techniques under different forms of uncertainty. We propose a comprehensive five-type taxonomy of environmental stochasticity and demonstrate systematic vulnerabilities in state-of-the-art model-based RL algorithms through targeted evaluation of DreamerV3 and STORM. Our findings reveal that world models dramatically underestimate environmental variance, struggle with action corruption, and exhibit unreliable dynamics under partial observability. We release the code and benchmark publicly at https://github.com/ARY2260/stori, providing a unified framework for developing more robust RL systems.

Global search and optimization of long-duration, low-thrust spacecraft trajectories with the indirect method is challenging due to a complex solution space and the difficulty of generating good initial guesses for the costate variables. This is particularly true in multibody environments. Given data that reveals a partial Pareto optimal front, it is desirable to find a flexible manner in which the Pareto front can be completed and fronts for related trajectory problems can be found. In this work we use conditional diffusion models to represent the distribution of candidate optimal trajectory solutions. We then introduce into this framework the novel approach of using Markov Chain Monte Carlo algorithms with self-supervised fine-tuning to achieve the aforementioned goals. Specifically, a random walk Metropolis algorithm is employed to propose new data that can be used to fine-tune the diffusion model using a reward-weighted training based on efficient evaluations of constraint violations and missions objective functions. The framework removes the need for separate focused and often tedious data generation phases. Numerical experiments are presented for two problems demonstrating the ability to improve sample quality and explicitly target Pareto optimality based on the theory of Markov chains. The first problem does so for a transfer in the Jupiter-Europa circular restricted three-body problem, where the MCMC approach completes a partial Pareto front. The second problem demonstrates how a dense and superior Pareto front can be generated by the MCMC self-supervised fine-tuning method for a Saturn-Titan transfer starting from the Jupiter-Europa case versus a separate dedicated global search.

B.4 Complete set of experimental results associated to section 4 In this section we display the complete set of results associated to figures shown in section 4. We

This paper aims at i) formally understanding equilibria reached by such agents, and ii) matching emergent phenomena of such equilibria to real-world targets. Parameter sharing with decentralized execution has been introduced as an efficient way to train multiple agents using a single policy network.

More recently, there has been a growing interest in automated analysis of high-dimensional video data collected during experiments. Here we introduce a probabilistic framework for the analysis of behavioral video and neural activity.

We consider online learning in episodic loop-free Markov decision processes (MDPs), where the loss function can change arbitrarily between episodes.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper proposes an estimation strategy for recovering the parameters of a finite state Markov chain given observed stationary frequencies of some states. Although the problem proposed is potentially very interesting, the paper does not appear to be in a mature state. Some fundamental issues are not adequately addressed, while the evaluation is limited, and the writing quality is not strong. Note that there is an uncountable set of ergodic transition models that can exactly match a given subset of stationary frequencies when the number of observed stationary state frequencies is small relative to the total number of states.

Neural Information Processing Systems http://nips.cc/