pith. sign in

Ofir Nachum

Identifiers

No identifiers captured yet.

Papers (22)

  1. OpenAI GPT-5 System Card cs.CL · 2025 · author #340
  2. Why Language Models Hallucinate cs.CL · 2025 · author #2
  3. OpenAI o1 System Card cs.AI · 2024 · author #185
  4. GPT-4o System Card cs.CL · 2024 · author #302
  5. RT-1: Robotics Transformer for Real-World Control at Scale cs.RO · 2022 · author #27
  6. D4RL: Datasets for Deep Data-Driven Reinforcement Learning cs.LG · 2020 · author #3
  7. Behavior Regularized Offline Reinforcement Learning cs.LG · 2019 · author #3
  8. DeepMDP: Learning Continuous Latent Space Models for Representation Learning cs.LG · 2019 · author #4
  9. Lyapunov-based Safe Policy Optimization for Continuous Control cs.LG · 2019 · author #2
  10. Identifying and Correcting Label Bias in Machine Learning cs.LG · 2019 · author #2
  11. The Laplacian in RL: Learning Representations with Efficient Approximations cs.LG · 2018 · author #3
  12. Near-Optimal Representation Learning for Hierarchical Reinforcement Learning cs.AI · 2018 · author #1
  13. Data-Efficient Hierarchical Reinforcement Learning cs.LG · 2018 · author #1
  14. A Lyapunov-based Approach to Safe Reinforcement Learning cs.LG · 2018 · author #2
  15. Smoothed Action Value Functions for Learning Gaussian Policies cs.LG · 2018 · author #1
  16. Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods cs.RO · 2018 · author #3
  17. Path Consistency Learning in Tsallis Entropy Regularized MDPs cs.AI · 2018 · author #1
  18. MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks cs.LG · 2017 · author #3
  19. Trust-PCL: An Off-Policy Trust Region Method for Continuous Control cs.AI · 2017 · author #1
  20. Learning to Remember Rare Events cs.LG · 2017 · author #2
  21. Bridging the Gap Between Value and Policy Based Reinforcement Learning cs.AI · 2017 · author #1
  22. Improving Policy Gradient by Exploring Under-appreciated Rewards cs.LG · 2016 · author #1

Mentions

No mention provenance yet.

Frequent Coauthors