Profiles2020-2025
Rishabh Agarwal
Google DeepMind
15Papers
2Last author
15Unique co-authors
6First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers15
- Generative Verifiers: Reward Modeling as Next-Token PredictionAuthor 6 of 6ICLR 2025
- Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved SamplingAuthor 8 of 14ICLR 2025
- Training Language Models to Self-Correct via Reinforcement LearningAuthor 3 of 19ICLR 2025
- On-Policy Distillation of Language Models: Learning from Self-Generated MistakesAuthor 1 of 8ICLR 2024 · 311 citations
- DistillSpec: Improving Speculative Decoding via Knowledge DistillationAuthor 8 of 9ICLR 2024 · 143 citations
- Stop Regressing: Training Value Functions via Classification for Scalable Deep RLAuthor 12 of 12ICML 2024 · 118 citations
- The Dormant Neuron Phenomenon in Deep Reinforcement LearningAuthor 2 of 4ICML 2023 · 153 citations
- Offline Q-learning on Diverse Multi-Task Data Both Scales And GeneralizesAuthor 2 of 5ICLR 2023 · 3 citations
- Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate ProgressAuthor 1 of 5NeurIPS 2022 · 95 citations
- DR3: Value-Based Deep Reinforcement Learning Requires Explicit RegularizationAuthor 2 of 7ICLR 2022 · 85 citations
- Deep Reinforcement Learning at the Edge of the Statistical PrecipiceAuthor 1 of 4NeurIPS 2021 · 1,067 citations
- Neural Additive Models: Interpretable Machine Learning with Neural NetsAuthor 1 of 7NeurIPS 2021 · 663 citations
- Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement LearningAuthor 2 of 5ICLR 2021 · 155 citations
- Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement LearningAuthor 1 of 4ICLR 2021 · 27 citations
- An Optimistic Perspective on Offline Reinforcement LearningAuthor 1 of 3ICML 2020 · 568 citations
