Lightning AI to host fireside chat on scaling RL with PyTorch for games
LightningAI · x · 2026-10-14
Lightning AI will host a fireside chat during PyTorch Conference on Oct 20 titled "Scaling RL on PyTorch: Monarch, TorchTitan, and What Games Demand." Game environments—real-time constraints, huge action spaces, and players quick to notice an off agent—are among the hardest places to train RL agents. Sarah Ahmed (ML Solutions Engineer, Lightning AI) moderates with Alireza Shamsoshoara (AI/ML Engineer, PyTorch team @ Meta). Agenda: 6:00 PM chat, 6:40 PM Q&A, 7:00 PM happy hour with retro arcade; registration required due to limited capacity.
More from coding & agent
- Anthropic built its own source control and migrated off git as merges hit 30K/day — itsOmSarraf_ · 2026-10-14
- Effect ships zero-dependency native test runner, agent-first — samgoodwin89 · 2026-10-14
- Codebases will look a lot like databases in the AI coding era — hargup13 · 2026-10-14
- Agent Argon reads Spot's SDK docs itself, builds trash-sorting skill on Boston Dynamics robot — chris_j_paxton · 2026-10-14
- Handling live web search in MCP agents without flooding the context window — Few_Training_8950 · 2026-10-14
- Developer runs Claude overnight to auto-localize Super Mario Odyssey on macOS — lxfater · 2026-10-14