CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinforcement Learning for Active Trading -- An Alpha-Reward Approach
This paper presents our system for Task 3 of the CLEF 2026 FinMMEval Lab, which requires daily long, flat, or short trading decisions for Bitcoin (BTC) and Tesla (TSLA) using news and historical market data. We formulate the problem as a discrete-action Markov Decision Process and compare four deep reinforcement learning algorithms: Policy Gradient (PG), Proximal Policy Optimization (PPO), Deep Q-Learning (DQL), and Deep Deterministic Policy Gradient (DDPG). The agents use technical indicators, cyclical calendar encodings, and daily news sentiment scores produced by LLaMA 3.2 1B. To reduce ove
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 87%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.94): “CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinfor” ≈ “aymericdamien/TopDeepLearning””
- FuzzySimilar title/name (fuzzy) · 66%stefan-jansen/machine-learning-for-trading →
“Fuzzy title match (0.78): “CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinfor” ≈ “stefan-jansen/machine-learning-for-trading””
- FuzzySimilar title/name (fuzzy) · 59%TauricResearch/TradingAgents →
“Fuzzy title match (0.73): “CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinfor” ≈ “TauricResearch/TradingAgents””
- FuzzySimilar title/name (fuzzy) · 59%HKUDS/Vibe-Trading →
“Fuzzy title match (0.73): “CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinfor” ≈ “HKUDS/Vibe-Trading””
- LinkedLinked via arxiv author · 85%Andrei Neagu →
“CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinforcement Learning for Active Trading -- An Alpha-Reward Approa”
- LinkedLinked via arxiv author · 85%Eeham Khan →
“CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinforcement Learning for Active Trading -- An Alpha-Reward Approa”
- LinkedLinked via arxiv author · 85%Leila Kosseim →
“CLaC@FinMMEval 2026 Task 3: Sentiment-Augmented Deep Reinforcement Learning for Active Trading -- An Alpha-Reward Approa”