├── .gitignore ├── LICENSE ├── README.md ├── assets ├── 0518_hist_step_m2.png ├── 0518_hist_wall_m2.png ├── 0518_scalar_step_m2.png ├── 0518_scalar_wall_m2.png ├── 0519_hist_step_all.png ├── 0519_hist_wall_all.png ├── 0519_scalar_step_all.png ├── 0519_scalar_wall_all.png ├── 0520_hist_step_all.png ├── 0520_hist_wall_all.png ├── 0520_scalar_step_all.png ├── 0520_scalar_wall_all.png ├── 0620_scalar_step_m2.png ├── 0620_scalar_step_m3.png ├── A1_0.00025lr_distributed.png ├── A1_A2_A4_0.00025lr.png ├── A1_A2_A4_0.00025lr_0.0025lr.png ├── A1_A2_A4_0.0025lr.png ├── A4_0.00025lr_distributed.png ├── A4_duel_double.png ├── best.gif ├── model.png ├── tensorboard_160516.png ├── tensorboard_160518_histogram1.png ├── tensorboard_160518_histogram2.png ├── tensorboard_160518_scalar1.png └── tensorboard_160518_scalar2.png ├── checkpoints └── Breakout-v0 │ └── min_delta--1 │ └── max_delta-1 │ └── history_length-4 │ └── train_frequency-4 │ └── target_q_update_step-10000 │ └── memory_size-1000000 │ └── action_repeat-4 │ └── ep_end_t-1000000 │ └── backend-tf │ └── random_start-30 │ └── scale-10000 │ └── env_type-simple │ └── min_reward--1.0 │ └── ep_start-1.0 │ └── screen_width-84 │ └── learn_start-50000.0 │ └── cnn_format-NCHW │ └── learning_rate-0.00025 │ └── batch_size-32 │ └── discount-0.99 │ └── max_reward-1.0 │ └── max_step-50000000 │ └── env_name-Breakout-v0 │ └── ep_end-0.1 │ └── model-m2 │ └── screen_height-84 │ ├── -16350000 │ ├── -16350000.meta │ └── checkpoint ├── config.py ├── dqn ├── __init__.py ├── agent.py ├── base.py ├── environment.py ├── history.py ├── ops.py ├── replay_memory.py └── utils.py └── main.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/README.md -------------------------------------------------------------------------------- /assets/0518_hist_step_m2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0518_hist_step_m2.png -------------------------------------------------------------------------------- /assets/0518_hist_wall_m2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0518_hist_wall_m2.png -------------------------------------------------------------------------------- /assets/0518_scalar_step_m2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0518_scalar_step_m2.png -------------------------------------------------------------------------------- /assets/0518_scalar_wall_m2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0518_scalar_wall_m2.png -------------------------------------------------------------------------------- /assets/0519_hist_step_all.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0519_hist_step_all.png -------------------------------------------------------------------------------- /assets/0519_hist_wall_all.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0519_hist_wall_all.png -------------------------------------------------------------------------------- /assets/0519_scalar_step_all.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0519_scalar_step_all.png -------------------------------------------------------------------------------- /assets/0519_scalar_wall_all.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0519_scalar_wall_all.png -------------------------------------------------------------------------------- /assets/0520_hist_step_all.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0520_hist_step_all.png -------------------------------------------------------------------------------- /assets/0520_hist_wall_all.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0520_hist_wall_all.png -------------------------------------------------------------------------------- /assets/0520_scalar_step_all.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0520_scalar_step_all.png -------------------------------------------------------------------------------- /assets/0520_scalar_wall_all.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0520_scalar_wall_all.png -------------------------------------------------------------------------------- /assets/0620_scalar_step_m2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0620_scalar_step_m2.png -------------------------------------------------------------------------------- /assets/0620_scalar_step_m3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/0620_scalar_step_m3.png -------------------------------------------------------------------------------- /assets/A1_0.00025lr_distributed.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/A1_0.00025lr_distributed.png -------------------------------------------------------------------------------- /assets/A1_A2_A4_0.00025lr.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/A1_A2_A4_0.00025lr.png -------------------------------------------------------------------------------- /assets/A1_A2_A4_0.00025lr_0.0025lr.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/A1_A2_A4_0.00025lr_0.0025lr.png -------------------------------------------------------------------------------- /assets/A1_A2_A4_0.0025lr.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/A1_A2_A4_0.0025lr.png -------------------------------------------------------------------------------- /assets/A4_0.00025lr_distributed.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/A4_0.00025lr_distributed.png -------------------------------------------------------------------------------- /assets/A4_duel_double.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/A4_duel_double.png -------------------------------------------------------------------------------- /assets/best.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/best.gif -------------------------------------------------------------------------------- /assets/model.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/model.png -------------------------------------------------------------------------------- /assets/tensorboard_160516.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/tensorboard_160516.png -------------------------------------------------------------------------------- /assets/tensorboard_160518_histogram1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/tensorboard_160518_histogram1.png -------------------------------------------------------------------------------- /assets/tensorboard_160518_histogram2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/tensorboard_160518_histogram2.png -------------------------------------------------------------------------------- /assets/tensorboard_160518_scalar1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/tensorboard_160518_scalar1.png -------------------------------------------------------------------------------- /assets/tensorboard_160518_scalar2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/assets/tensorboard_160518_scalar2.png -------------------------------------------------------------------------------- /checkpoints/Breakout-v0/min_delta--1/max_delta-1/history_length-4/train_frequency-4/target_q_update_step-10000/memory_size-1000000/action_repeat-4/ep_end_t-1000000/backend-tf/random_start-30/scale-10000/env_type-simple/min_reward--1.0/ep_start-1.0/screen_width-84/learn_start-50000.0/cnn_format-NCHW/learning_rate-0.00025/batch_size-32/discount-0.99/max_reward-1.0/max_step-50000000/env_name-Breakout-v0/ep_end-0.1/model-m2/screen_height-84/-16350000: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/checkpoints/Breakout-v0/min_delta--1/max_delta-1/history_length-4/train_frequency-4/target_q_update_step-10000/memory_size-1000000/action_repeat-4/ep_end_t-1000000/backend-tf/random_start-30/scale-10000/env_type-simple/min_reward--1.0/ep_start-1.0/screen_width-84/learn_start-50000.0/cnn_format-NCHW/learning_rate-0.00025/batch_size-32/discount-0.99/max_reward-1.0/max_step-50000000/env_name-Breakout-v0/ep_end-0.1/model-m2/screen_height-84/-16350000 -------------------------------------------------------------------------------- /checkpoints/Breakout-v0/min_delta--1/max_delta-1/history_length-4/train_frequency-4/target_q_update_step-10000/memory_size-1000000/action_repeat-4/ep_end_t-1000000/backend-tf/random_start-30/scale-10000/env_type-simple/min_reward--1.0/ep_start-1.0/screen_width-84/learn_start-50000.0/cnn_format-NCHW/learning_rate-0.00025/batch_size-32/discount-0.99/max_reward-1.0/max_step-50000000/env_name-Breakout-v0/ep_end-0.1/model-m2/screen_height-84/-16350000.meta: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/checkpoints/Breakout-v0/min_delta--1/max_delta-1/history_length-4/train_frequency-4/target_q_update_step-10000/memory_size-1000000/action_repeat-4/ep_end_t-1000000/backend-tf/random_start-30/scale-10000/env_type-simple/min_reward--1.0/ep_start-1.0/screen_width-84/learn_start-50000.0/cnn_format-NCHW/learning_rate-0.00025/batch_size-32/discount-0.99/max_reward-1.0/max_step-50000000/env_name-Breakout-v0/ep_end-0.1/model-m2/screen_height-84/-16350000.meta -------------------------------------------------------------------------------- /checkpoints/Breakout-v0/min_delta--1/max_delta-1/history_length-4/train_frequency-4/target_q_update_step-10000/memory_size-1000000/action_repeat-4/ep_end_t-1000000/backend-tf/random_start-30/scale-10000/env_type-simple/min_reward--1.0/ep_start-1.0/screen_width-84/learn_start-50000.0/cnn_format-NCHW/learning_rate-0.00025/batch_size-32/discount-0.99/max_reward-1.0/max_step-50000000/env_name-Breakout-v0/ep_end-0.1/model-m2/screen_height-84/checkpoint: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/checkpoints/Breakout-v0/min_delta--1/max_delta-1/history_length-4/train_frequency-4/target_q_update_step-10000/memory_size-1000000/action_repeat-4/ep_end_t-1000000/backend-tf/random_start-30/scale-10000/env_type-simple/min_reward--1.0/ep_start-1.0/screen_width-84/learn_start-50000.0/cnn_format-NCHW/learning_rate-0.00025/batch_size-32/discount-0.99/max_reward-1.0/max_step-50000000/env_name-Breakout-v0/ep_end-0.1/model-m2/screen_height-84/checkpoint -------------------------------------------------------------------------------- /config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/config.py -------------------------------------------------------------------------------- /dqn/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /dqn/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/dqn/agent.py -------------------------------------------------------------------------------- /dqn/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/dqn/base.py -------------------------------------------------------------------------------- /dqn/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/dqn/environment.py -------------------------------------------------------------------------------- /dqn/history.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/dqn/history.py -------------------------------------------------------------------------------- /dqn/ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/dqn/ops.py -------------------------------------------------------------------------------- /dqn/replay_memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/dqn/replay_memory.py -------------------------------------------------------------------------------- /dqn/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/dqn/utils.py -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/devsisters/DQN-tensorflow/HEAD/main.py --------------------------------------------------------------------------------