← authors · overview

• CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms
  2021 · 86 citations
• Zephyr: Direct Distillation of LM Alignment
  2023 · 56 citations
• EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine
  2022 · 14 citations
• Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games
  2020 · 5 citations
• Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning
  2024 · 3 citations
• 2 OLMo 2 Furious
  2025 · 2 citations
• Gym-$μ$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning
  2021 · 2 citations
• Comparing Observation and Action Representations for Deep Reinforcement Learning in $μ$RTS
  2019
• Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform
  2023
• Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks
  2023
• Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
  2024
• Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
  2024