Rishabh Agarwal

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models ICLR 2025 Generative Verifiers: Reward Modeling as Next-Token Prediction ICLR 2025 Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models ICLR 2025 Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs ICML 2025 Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning ICLR 2025 Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling ICLR 2025 Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling ICLR 2025 Training Language Models to Self-Correct via Reinforcement Learning ICLR 2025 DistillSpec: Improving Speculative Decoding via Knowledge Distillation ICLR 2024 Many-Shot In-Context Learning NeurIPS 2024 On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes ICLR 2024 On scalable oversight with weak LLMs judging strong LLMs NeurIPS 2024 SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning ICML 2024 Stop Regressing: Training Value Functions via Classification for Scalable Deep RL ICML 2024 A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces AISTATS 2023 Bigger, Better, Faster: Human-level Atari with human-level efficiency ICML 2023 Bootstrapped Representations in Reinforcement Learning ICML 2023 Investigating Multi-task Pretraining and Generalization in Reinforcement Learning ICLR 2023 Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes ICLR 2023 Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks ICLR 2023 Revisiting Bellman Errors for Offline Model Selection ICML 2023 The Dormant Neuron Phenomenon in Deep Reinforcement Learning ICML 2023 Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research NeurIPS 2023 Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation AAAI 2022 DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization ICLR 2022 On the Generalization of Representations in Reinforcement Learning AISTATS 2022 Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress NeurIPS 2022 Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning ICLR 2021 Deep Reinforcement Learning at the Edge of the Statistical Precipice NeurIPS 2021 Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning ICLR 2021 Neural Additive Models: Interpretable Machine Learning with Neural Nets NeurIPS 2021 An Optimistic Perspective on Offline Reinforcement Learning ICML 2020 IITK at SemEval-2020 Task 10: Transformers for Emphasis Selection SemEval 2020 Revisiting Fundamentals of Experience Replay ICML 2020 RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning NeurIPS 2020 Learning to Generalize from Sparse and Underspecified Rewards ICML 2019