| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context M Reid, N Savinov, D Teplyashin, D Lepikhin, T Lillicrap, J Alayrac, ... arXiv preprint arXiv:2403.05530, *Core Contributor, 2024 | 1370 | 2024 |
| Deep Reinforcement Learning at the Edge of the Statistical Precipice R Agarwal, M Schwarzer, PS Castro, A Courville, MG Bellemare Neural Information Processing Systems (NeurIPS), 𝗢𝘂𝘁𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴 𝗣𝗮𝗽𝗲𝗿 𝗔𝘄𝗮𝗿𝗱, 2021 | 780 | 2021 |
| An Optimistic Perspective on Offline Reinforcement Learning R Agarwal, D Schuurmans, M Norouzi International Conference on Machine Learning (ICML), 2020 | 755* | 2020 |
| Gemma 2: Improving open language models at a practical size G Team, M Riviere, S Pathak, PG Sessa, C Hardin, S Bhupatiraju, ... arXiv preprint arXiv:2408.00118, 2024 | 567 | 2024 |
| Neural additive models: Interpretable machine learning with neural nets R Agarwal, L Melnick, Frosst, Zhang, Lengerich, R Caruana, GE Hinton Neural Information Processing Systems (NeurIPS), 𝗦𝗽𝗼𝘁𝗹𝗶𝗴𝗵𝘁, 2021 | 564 | 2021 |
| Revisiting Fundamentals of Experience Replay W Fedus*, P Ramachandran*, R Agarwal, Y Bengio, H Larochelle, ... International Conference on Machine Learning (ICML), 2020 | 342 | 2020 |
| RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning C Gulcehre, Z Wang, A Novikov, T Paine, S Gómez, K Zolna, R Agarwal, ... Advances in Neural Information Processing Systems (NeurIPS), 2020 | 225* | 2020 |
| Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning R Agarwal, MC Machado, PS Castro, MG Bellemare International Conference on Learning Representations (ICLR), 𝗦𝗽𝗼𝘁𝗹𝗶𝗴𝗵𝘁, 2021 | 220 | 2021 |
| On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes R Agarwal*, N Vieillard*, Y Zhou, P Stanczyk, S Ramos, M Geist, ... International Conference on Learning Representations (ICLR), 2024 | 173* | 2024 |
| Many-shot in-context learning R Agarwal, A Singh, LM Zhang, B Bohnet, S Chan, A Anand, Z Abbas, ... Neural Information Processing Systems (NeurIPS), 𝗦𝗽𝗼𝘁𝗹𝗶𝗴𝗵𝘁, 2024 | 156* | 2024 |
| Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning A Kumar*, R Agarwal*, D Ghosh, S Levine International Conference on Learning Representations (ICLR), *equal contribution, 2021 | 126 | 2021 |
| Learning to Generalize from Sparse and Underspecified Rewards R Agarwal, C Liang, D Schuurmans, M Norouzi International Conference on Machine Learning (ICML), 2019 | 116 | 2019 |
| Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models A Singh*, JD Co-Reyes*, R Agarwal*, A Anand, P Patil, PJ Liu, J Harrison, ... Transactions on Machine Learning Research (TMLR), 2024 | 108 | 2024 |
| Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research C Gulino, J Fu, W Luo, G Tucker, E Bronstein, Y Lu, J Harb, X Pan, ... Neural Information Processing Systems, NeurIPS, 2023 | 106 | 2023 |
| The Dormant Neuron Phenomenon in Deep Reinforcement Learning G Sokar, R Agarwal, PS Castro, U Evci International Conference on Machine Learning (ICML), 𝐎𝐫𝐚𝐥, 2023 | 103 | 2023 |
| Generative verifiers: Reward modeling as next-token prediction L Zhang, A Hosseini, H Bansal, M Kazemi, A Kumar, R Agarwal International Conference on Learning Representations (ICLR), 2025 | 99* | 2025 |
| Training Language Models to Self-Correct via Reinforcement Learning A Kumar*, V Zhuang*, R Agarwal*, Y Su*, JD Co-Reyes, A Singh, ... International Conference on Learning Representations (ICLR), 𝐎𝐫𝐚𝐥, 2025 | 97* | 2025 |
| Bigger, Better, Faster: Human-level Atari with human-level efficiency M Schwarzer, JO Ceron, Courville, Bellemare, PS Castro*, R Agarwal* International Conference on Machine Learning (ICML), 2023 | 93 | 2023 |
| V-star: Training verifiers for self-taught reasoners A Hosseini, X Yuan, N Malkin, A Courville, A Sordoni, R Agarwal Conference on Language Modelling (CoLM), 2024 | 89 | 2024 |
| Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress R Agarwal, M Schwarzer, PS Castro, A Courville, MG Bellemare Neural Information Processing Systems (NeurIPS), 2022 | 85* | 2022 |
Marc G. BellemareReliant AIVerified email at reliant.ai
