Fetching metadata from the HF Docker repository... - .agents feat: enhance reward configuration management with new logging functions, add parallel Modal training guidelines to documentation, and improve reward config hashing for deterministic behavior
- .codex feat: integrate Trackio for experiment tracking, add GRPO training support, and deploy web-based monitoring tools
- assets diagrams updated
- blog Add mini-blog
- configs feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment
- scripts feat: introduce GRPO GPU fallback support, enhance training script with warmstart tagging, and add learning rate parameter for improved training flexibility
- server feat: enhance CyberSecurity_OWASP observation model with scenario prompt, improve GRPO batch configuration validation, and add scenario grouping for adaptive difficulty curriculum
- tests feat: introduce GRPO GPU fallback support, enhance training script with warmstart tagging, and add learning rate parameter for improved training flexibility
- training feat: introduce GRPO GPU fallback support, enhance training script with warmstart tagging, and add learning rate parameter for improved training flexibility
- 100 Bytes feat: implement core RL training infrastructure and architecture documentation
- 82 Bytes feat: integrate Trackio for experiment tracking and add Modal training infrastructure with environment and test utilities.
- 163 Bytes feat: implement core RL training infrastructure and architecture documentation
- 6.97 kB feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment
- 20 kB feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment
- 38.4 kB feat: enhance reward configuration management with new logging functions, add parallel Modal training guidelines to documentation, and improve reward config hashing for deterministic behavior
- 927 Bytes feat: integrate Trackio for experiment tracking and add Modal training infrastructure with environment and test utilities.
- 20.3 kB Add mini-blog
- 594 Bytes feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts.
- 692 Bytes feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts.
- 1.26 kB feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts.
- 7.72 kB feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment
- 2.91 kB feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment
- 537 Bytes feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts.
- 3.88 kB feat: enhance CyberSecurity_OWASP observation model with scenario prompt, improve GRPO batch configuration validation, and add scenario grouping for adaptive difficulty curriculum
- 103 Bytes Initial commit
- 3.48 kB feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts.
- 1.78 kB feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment
- 10.2 kB feat: introduce reward ablation configurations for enhanced training flexibility, implement YAML loading with extends support, and add reward variant tracking in training scripts
- 15.7 kB feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment
- 420 Bytes feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts.
- 680 Bytes feat: implement RL environment server with training infrastructure and Modal integration
- 2.86 kB feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts.
- 817 kB feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment
- 10.7 kB feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment
