BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Aleksei Shpilman

Aleksei Shpilman contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningArtificial IntelligenceComputer VisionMultiagent SystemsRobotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
7works
0followers
5topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

7 published item(s)

preprint2026arXiv

SDG-MoE: Signed Debate Graph Mixture-of-Experts

Sparse MoE models achieve a good balance between capacity and compute by routing each token to a small subset of experts. However, in most MoE architectures, once a token is routed, the selected experts process it independently and their outputs are combined via a weighted sum. This leaves open whether enabling communication among them could improve performance. While prior work has raised this question, direct interaction among the active routed experts remains underexplored. In this paper, we propose SDG-MoE (Signed Debate Graph Mixture-of-Experts), a novel architecture that adds a lightweight, iterative deliberation step before final aggregation. SDG-MoE introduces three components: (i) two learned interaction matrices over the active experts, a support graph $A^+$ and a critique graph $A^-$, capturing reinforcing and corrective influences; (ii) a signed message-passing step that updates expert representations before aggregation; and (iii) a disagreement-gated Friedkin-Johnsen-style anchoring that controls deliberation strength while preventing expert drift. Together, these enable a structured deliberation process where interaction strength scales with disagreement and specialization is preserved. We also provide a theoretical analysis establishing stability conditions on expert states and showing that deliberation adds only low-order overhead over the active set. In controlled three-seed pretraining experiments, SDG-MoE improves validation perplexity over both an unsigned graph communication baseline and vanilla MoE, outperforming the strongest baseline by 19.8%, and gives the best external perplexity on WikiText-103, C4, and Paloma among the compared systems.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Improving State-of-the-Art in One-Class Classification by Leveraging Unlabeled Data

When dealing with binary classification of data with only one labeled class data scientists employ two main approaches, namely One-Class (OC) classification and Positive Unlabeled (PU) learning. The former only learns from labeled positive data, whereas the latter also utilizes unlabeled data to improve the overall performance. Since PU learning utilizes more data, we might be prone to think that when unlabeled data is available, the go-to algorithms should always come from the PU group. However, we find that this is not always the case if unlabeled data is unreliable, i.e. contains limited or biased latent negative data. We perform an extensive experimental study of a wide list of state-of-the-art OC and PU algorithms in various scenarios as far as unlabeled data reliability is concerned. Furthermore, we propose PU modifications of state-of-the-art OC algorithms that are robust to unreliable unlabeled data, as well as a guideline to similarly modify other OC algorithms. Our main practical recommendation is to use state-of-the-art PU algorithms when unlabeled data is reliable and to use the proposed modifications of state-of-the-art OC algorithms otherwise. Additionally, we outline procedures to distinguish the cases of reliable and unreliable unlabeled data using statistical tests.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Scalable Multi-Agent Model-Based Reinforcement Learning

Recent Multi-Agent Reinforcement Learning (MARL) literature has been largely focused on Centralized Training with Decentralized Execution (CTDE) paradigm. CTDE has been a dominant approach for both cooperative and mixed environments due to its capability to efficiently train decentralized policies. While in mixed environments full autonomy of the agents can be a desirable outcome, cooperative environments allow agents to share information to facilitate coordination. Approaches that leverage this technique are usually referred as communication methods, as full autonomy of agents is compromised for better performance. Although communication approaches have shown impressive results, they do not fully leverage this additional information during training phase. In this paper, we propose a new method called MAMBA which utilizes Model-Based Reinforcement Learning (MBRL) to further leverage centralized training in cooperative environments. We argue that communication between agents is enough to sustain a world model for each agent during execution phase while imaginary rollouts can be used for training, removing the necessity to interact with the environment. These properties yield sample efficient algorithm that can scale gracefully with the number of agents. We empirically confirm that MAMBA achieves good performance while reducing the number of interactions with the environment up to an orders of magnitude compared to Model-Free state-of-the-art approaches in challenging domains of SMAC and Flatland.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Self-Imitation Learning from Demonstrations

Despite the numerous breakthroughs achieved with Reinforcement Learning (RL), solving environments with sparse rewards remains a challenging task that requires sophisticated exploration. Learning from Demonstrations (LfD) remedies this issue by guiding the agent's exploration towards states experienced by an expert. Naturally, the benefits of this approach hinge on the quality of demonstrations, which are rarely optimal in realistic scenarios. Modern LfD algorithms require meticulous tuning of hyperparameters that control the influence of demonstrations and, as we show in the paper, struggle with learning from suboptimal demonstrations. To address these issues, we extend Self-Imitation Learning (SIL), a recent RL algorithm that exploits the agent's past good experience, to the LfD setup by initializing its replay buffer with demonstrations. We denote our algorithm as SIL from Demonstrations (SILfD). We empirically show that SILfD can learn from demonstrations that are noisy or far from optimal and can automatically adjust the influence of demonstrations throughout the training without additional hyperparameters or handcrafted schedules. We also find SILfD superior to the existing state-of-the-art LfD algorithms in sparse environments, especially when demonstrations are highly suboptimal.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes

The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future on simply aggregated GPS probe data in time and space bins. We thus reinterpreted the challenge of forecasting traffic conditions as a movie completion task. U-Nets proved to be the winning architecture, demonstrating an ability to extract relevant features in this complex real-world geo-spatial process. Building on the previous competitions, Traffic4cast 2021 now focuses on the question of model robustness and generalizability across time and space. Moving from one city to an entirely different city, or moving from pre-COVID times to times after COVID hit the world thus introduces a clear domain shift. We thus, for the first time, release data featuring such domain shifts. The competition now covers ten cities over 2 years, providing data compiled from over 10^12 GPS probe data. Winning solutions captured traffic dynamics sufficiently well to even cope with these complex domain shifts. Surprisingly, this seemed to require only the previous 1h traffic dynamic history and static road graph as input.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments

Recent reinforcement learning studies extensively explore the interplay between cooperative and competitive behaviour in mixed environments. Unlike cooperative environments where agents strive towards a common goal, mixed environments are notorious for the conflicts of selfish and social interests. As a consequence, purely rational agents often struggle to achieve and maintain cooperation. A prevalent approach to induce cooperative behaviour is to assign additional rewards based on other agents' well-being. However, this approach suffers from the issue of multi-agent credit assignment, which can hinder performance. This issue is efficiently alleviated in cooperative setting with such state-of-the-art algorithms as QMIX and COMA. Still, when applied to mixed environments, these algorithms may result in unfair allocation of rewards. We propose BAROCCO, an extension of these algorithms capable to balance individual and social incentives. The mechanism behind BAROCCO is to train two distinct but interwoven components that jointly affect each agent's decisions. Our meta-algorithm is compatible with both Q-learning and Actor-Critic frameworks. We experimentally confirm the advantages over the existing methods and explore the behavioural aspects of BAROCCO in two mixed multi-agent setups.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Imitation Learning Approach for AI Driving Olympics Trained on Real-world and Simulation Data Simultaneously

In this paper, we describe our winning approach to solving the Lane Following Challenge at the AI Driving Olympics Competition through imitation learning on a mixed set of simulation and real-world data. AI Driving Olympics is a two-stage competition: at stage one, algorithms compete in a simulated environment with the best ones advancing to a real-world final. One of the main problems that participants encounter during the competition is that algorithms trained for the best performance in simulated environments do not hold up in a real-world environment and vice versa. Classic control algorithms also do not translate well between tasks since most of them have to be tuned to specific driving conditions such as lighting, road type, camera position, etc. To overcome this problem, we employed the imitation learning algorithm and trained it on a dataset collected from sources both from simulation and real-world, forcing our model to perform equally well in all environments.

0 citations0 reviewsNo code linkedOpen access