Evgenii Nikishin

7 papers · 2022–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (17) 🏆 Grand Slam 👑 Triple Crown

Venues

ICLR (3) ICML (2) AAAI (1) NeurIPS (1)

Top co-authors

Aaron Courville (4) Pierre-Luc Bacon (3) Razvan Pascanu (2) Pierluca D'Oro (2) Zhixuan Lin (2) Will Dabney (2) Max Schwarzer (2) Clare Lyle (2) Bernardo Avila Pires (1) Xu He (1)

Research topics

Deep Learning (5) Machine Learning (5) Reinforcement Learning (5) Methods (5) Learning Types · Deep Learning (4) Optimization & Theory (3) Artificial Intelligence (2) Applications (2) Core AI (2) Core Methods (2) Learning Types · Machine Learning (2) Architectures (1) Models (1) Techniques (1)

Keywords

deep reinforcement learning (4) sample efficiency (2) neural network plasticity (2) reinforcement learning (2) loss landscape (1) maximum likelihood (1) model-based reinforcement learning (1) off-policy learning (1) maximum likelihood estimation (1) implicit differentiation (1) plasticity loss (1) control task (1) parameter reset (1) length extrapolation (1) experience replay (1) cognitive science (1) long-context modeling (1) atari benchmark (1) forget gate (1) replay ratio (1)

Papers

Forgetting Transformer: Softmax Attention with a Forget Gate ICLR 2025 The Curse of Diversity in Ensemble-Based Exploration ICLR 2024 Deep Reinforcement Learning with Plasticity Injection NeurIPS 2023 Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier ICLR 2023 Understanding Plasticity in Neural Networks ICML 2023 Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation AAAI 2022 The Primacy Bias in Deep Reinforcement Learning ICML 2022