├── Baseline_data ├── alive ├── avg_losses ├── epochs ├── losses ├── net_reward └── total_steps ├── D3QN.py ├── D3QN_Agent.py ├── D3QN_data ├── alive ├── avg_losses ├── epochs ├── net_reward ├── total_loss_per_step.png └── total_steps ├── DQN ├── DQNet.py ├── DQNet_Agent.py ├── __init__.py └── prioritized_replay_buffer.py ├── DQN_data ├── alive ├── alive_per_epcoh.png ├── average_loss_per_epoch.png ├── avg_losses ├── epochs ├── net_reward ├── reward_per_epoch.png ├── total_loss_per_steppng.png └── total_steps ├── README.md ├── RandomAgent.py ├── __pycache__ ├── DQNet.cpython-36.pyc ├── DQNet_Agent.cpython-36.pyc ├── RandomAgent.cpython-36.pyc ├── prioritized_replay_buffer.cpython-36.pyc └── segment_tree.cpython-36.pyc ├── losses.zip ├── prioritized_replay_buffer.py ├── segment_tree.py └── train.py /Baseline_data/alive: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/Baseline_data/alive -------------------------------------------------------------------------------- /Baseline_data/avg_losses: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/Baseline_data/avg_losses -------------------------------------------------------------------------------- /Baseline_data/epochs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/Baseline_data/epochs -------------------------------------------------------------------------------- /Baseline_data/losses: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/Baseline_data/losses -------------------------------------------------------------------------------- /Baseline_data/net_reward: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/Baseline_data/net_reward -------------------------------------------------------------------------------- /Baseline_data/total_steps: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/Baseline_data/total_steps -------------------------------------------------------------------------------- /D3QN.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/D3QN.py -------------------------------------------------------------------------------- /D3QN_Agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/D3QN_Agent.py -------------------------------------------------------------------------------- /D3QN_data/alive: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/D3QN_data/alive -------------------------------------------------------------------------------- /D3QN_data/avg_losses: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/D3QN_data/avg_losses -------------------------------------------------------------------------------- /D3QN_data/epochs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/D3QN_data/epochs -------------------------------------------------------------------------------- /D3QN_data/net_reward: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/D3QN_data/net_reward -------------------------------------------------------------------------------- /D3QN_data/total_loss_per_step.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/D3QN_data/total_loss_per_step.png -------------------------------------------------------------------------------- /D3QN_data/total_steps: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/D3QN_data/total_steps -------------------------------------------------------------------------------- /DQN/DQNet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN/DQNet.py -------------------------------------------------------------------------------- /DQN/DQNet_Agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN/DQNet_Agent.py -------------------------------------------------------------------------------- /DQN/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /DQN/prioritized_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN/prioritized_replay_buffer.py -------------------------------------------------------------------------------- /DQN_data/alive: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN_data/alive -------------------------------------------------------------------------------- /DQN_data/alive_per_epcoh.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN_data/alive_per_epcoh.png -------------------------------------------------------------------------------- /DQN_data/average_loss_per_epoch.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN_data/average_loss_per_epoch.png -------------------------------------------------------------------------------- /DQN_data/avg_losses: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN_data/avg_losses -------------------------------------------------------------------------------- /DQN_data/epochs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN_data/epochs -------------------------------------------------------------------------------- /DQN_data/net_reward: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN_data/net_reward -------------------------------------------------------------------------------- /DQN_data/reward_per_epoch.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN_data/reward_per_epoch.png -------------------------------------------------------------------------------- /DQN_data/total_loss_per_steppng.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN_data/total_loss_per_steppng.png -------------------------------------------------------------------------------- /DQN_data/total_steps: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/DQN_data/total_steps -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/README.md -------------------------------------------------------------------------------- /RandomAgent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/RandomAgent.py -------------------------------------------------------------------------------- /__pycache__/DQNet.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/__pycache__/DQNet.cpython-36.pyc -------------------------------------------------------------------------------- /__pycache__/DQNet_Agent.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/__pycache__/DQNet_Agent.cpython-36.pyc -------------------------------------------------------------------------------- /__pycache__/RandomAgent.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/__pycache__/RandomAgent.cpython-36.pyc -------------------------------------------------------------------------------- /__pycache__/prioritized_replay_buffer.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/__pycache__/prioritized_replay_buffer.cpython-36.pyc -------------------------------------------------------------------------------- /__pycache__/segment_tree.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/__pycache__/segment_tree.cpython-36.pyc -------------------------------------------------------------------------------- /losses.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/losses.zip -------------------------------------------------------------------------------- /prioritized_replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/prioritized_replay_buffer.py -------------------------------------------------------------------------------- /segment_tree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/segment_tree.py -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jeffreytsaw/PowerGridRLAgent/HEAD/train.py --------------------------------------------------------------------------------