Session on Deep Reinforcement Learning based Trading DRL is currently being investigated in the area of algorithmic trading, and forecasting because of the adaptability of algorithms in diverse environments. DRL follows 2 major approaches: - Model Free RL - Model Based RL In generic DRL, the trading Agent is responsible for executing all call actions (buy, hold, sell) and is sometimes moderated by other Agents. There can be several variations in Agent based DRL which includes mutual collaboration across Agents, dueling or competition between the Agents, to creating diverse complex Environments. In this segment, we will be focussing on creating Agents which can identify to take actions - buy,hold and sell depending on the current share prices, treasury rates and penalties. The Agent gets a reward if it is able to attain a profit at the end of a trading period and is rewarded with a penalty in all cases (including cases where opportunities were missed). Model Free RL encompasses the class of algorithms which focus on a specific set of goals and performs optimization of the reward funct

⚠ No verified equity curve — no track-record source connected.

No score history is stored yet — only the current score is shown.

⚠ No live verification account connected — ask for proof before buying.

Alerts on changes: coming soon

Prop-firm compatibility not provided.

Data-completeness & trust index (not a profitability rating)