Reinforcement-learning aggregator on top of the TradingAgents multi-agent LLM trading framework. PPO policy that beats buy-and-hold on the 2026 YTD test across two LLM backbones (Anthropic + OpenAI); cross-LLM transfer holds. Course project, Columbia IEORE 4733.
python nlp reinforcement-learning pytorch course-project quantitative-finance algorithmic-trading backtesting ppo sentence-transformers financial-ml multi-agent-llm tradingagents columbia-ieor
-
Updated
May 12, 2026 - Python