RL-Portfolio-Allocator

A portfolio allocation system using Reinforcement Learning Techniques

Available RL Models

• Advantage Actor Critic (A2C)
• Deep Deterministic Policy Gradient (DDPG)
• Soft Actor Critic (SAC)
• Proximal Policy Optimization (PPO)

Training

To train a model, use train.py python script.

python train.py <model_name> <start_date> <end_date> [OPTIONAL - initial_amount]

Note

• For training, use any one of the available models (a2c, ddpg, sac, ppo).

The pretrained trained models are stored in portfolio_manager/trained_models.