← authors · overview

• Acme: A Research Framework for Distributed Reinforcement Learning
  2020 · 73 citations
• RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
  2023 · 69 citations
• Adversarially Guided Actor-Critic
  2021 · 11 citations
• Self-Imitation Advantage Learning
  2020 · 8 citations
• Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act
  2022 · 4 citations
• WARM: On the Benefits of Weight Averaged Reward Models
  2024 · 3 citations
• Direct Language Model Alignment from Online AI Feedback
  2024 · 3 citations
• There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning
  2021 · 2 citations
• A Survey of Temporal Credit Assignment in Deep Reinforcement Learning
  2023 · 1 citations
• WARP: On the Benefits of Weight Averaged Rewarded Policies
  2024 · 1 citations
• More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences
  2021
• Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL
  2024