
Description
Training trading strategies with RL means building market environments, action spaces and rewards from scratch. TensorTrade is an open-source reinforcement learning framework for training, evaluating and deploying trading agents.
It breaks exchanges, data, actions and rewards into composable modules for fast experimentation.
Environments:Composable.
Rewards:Custom goals.
Evaluation:Backtests.
Deploy:Live-ready.
It breaks exchanges, data, actions and rewards into composable modules for fast experimentation.
Features
Environments:Composable.
Rewards:Custom goals.
Evaluation:Backtests.
Deploy:Live-ready.
