← Authors

Aviral Kumar

58 papers · 2018–2025 · 6 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (12) 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (7) 🐝 Cross-Pollinator (8) 🌈 Renaissance Researcher (7) πŸ”¬ Deep Specialist (15) 🀝 Dynamic Duo (45) πŸ‘₯ Mega-Team (25) πŸ† Keyword Champion (2) πŸ‘‘ Triple Crown πŸ—ƒοΈ Keyword Collector (131) ❓ The Questioner (3) ⚑ Prolific Year (5) πŸ”₯ Unstoppable (8) πŸ’Ž Century Club (58)

Conferences

ICLR (19) NIPS (19) ICML (12) CORL (6) NAACL (1) RSS (1)

Top co-authors

Sergey Levine (45) Chelsea Finn (10) Rishabh Agarwal (8) XINYANG GENG (6) Anikait Singh (6) George Tucker (6) Yevgen Chebotar (6) Amrith Setlur (5) Tianhe Yu (5) Quan Vuong (4)

Research topics

Reinforcement Learning (1)

Keywords

offline reinforcement learning (16) reinforcement learning (7) model-based optimization (5) distributional shift (4) conservative q-learning (4) value function (4) policy learning (4) robot manipulation (3) robotic manipulation (3) large language model (3) distribution shift (3) imitation learning (2) multi-task learning (2) offline optimization (2) model-free learning (2) deep reinforcement learning (2) few-shot learning (2) dynamic programming (2) black-box optimization (2) continuous control (2)

Papers

Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning ICLR 2025
What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning? ICML 2025
RRM: Robust Reward Model Training Mitigates Reward Hacking ICLR 2025
Training Language Models to Self-Correct via Reinforcement Learning ICLR 2025
Unfamiliar Finetuning Examples Control How Language Models Hallucinate NAACL 2025
Scaling Test-Time Compute Without Verification or RL is Suboptimal ICML 2025
Value-Based Deep RL Scales Predictably ICML 2025
Generative Verifiers: Reward Modeling as Next-Token Prediction ICLR 2025
Digi-Q: Learning VLM Q-Value Functions for Training Device-Control Agents ICLR 2025
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models ICLR 2025
Optimizing Test-Time Compute via Meta Reinforcement Finetuning ICML 2025
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning ICLR 2025
Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data ICLR 2025
Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance CORL 2024
Recursive Introspection: Teaching Language Model Agents How to Self-Improve NIPS 2024
Is Value Learning Really the Main Bottleneck in Offline RL? NIPS 2024
Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models ICLR 2024
Designing Cell-Type-Specific Promoter Sequences Using Conservative Model-Based Optimization NIPS 2024
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL ICML 2024
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data ICML 2024
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL ICML 2024
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning NIPS 2024
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold NIPS 2024
Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning CORL 2023
Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets NIPS 2023
ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints NIPS 2023
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning NIPS 2023
Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions CORL 2023
Efficient Deep Reinforcement Learning Requires Regulating Overfitting ICLR 2023
Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes ICLR 2023
Confidence-Conditioned Value Functions for Offline Reinforcement Learning ICLR 2023
Pre-Training for Robots: Offline RL Enables Learning New Tasks in a Handful of Trials RSS 2023
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization ICLR 2022
DASCO: Dual-Generator Adversarial Support Constrained Offline Reinforcement Learning NIPS 2022
Data-Driven Offline Decision-Making via Invariant Representation Learning NIPS 2022
Data-Driven Offline Optimization for Architecting Hardware Accelerators ICLR 2022
Don’t Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning CORL 2022
Should I Run Offline Reinforcement Learning or Behavioral Cloning? ICLR 2022
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization ICML 2022
How to Leverage Unlabeled Data in Offline Reinforcement Learning ICML 2022
Conservative Objective Models for Effective Offline Model-Based Optimization ICML 2021
A Workflow for Offline Model-Free Robotic Reinforcement Learning CORL 2021
Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability NIPS 2021
Conservative Data Sharing for Multi-Task Offline Reinforcement Learning NIPS 2021
Conservative Safety Critics for Exploration ICLR 2021
Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning ICLR 2021
Benchmarks for Deep Off-Policy Evaluation ICLR 2021
COMBO: Conservative Offline Model-Based Policy Optimization NIPS 2021
OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning ICLR 2021
Model Inversion Networks for Model-Based Optimization NIPS 2020
Conservative Q-Learning for Offline Reinforcement Learning NIPS 2020
Chaining Behaviors from Data with Model-Free Reinforcement Learning CORL 2020
DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction NIPS 2020
One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL NIPS 2020
Diagnosing Bottlenecks in Deep Q-learning Algorithms ICML 2019
Graph Normalizing Flows NIPS 2019
Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction NIPS 2019
Trainable Calibration Measures for Neural Networks from Kernel Mean Embeddings ICML 2018