config.yaml

# Filename: config.yaml
# Description: Contains configuration variables for navigation project
# Author: Thomas Wood (odell.wood@gmail.com)

# Parameters for the Unity Environment
Environment:
  # location of executable
  Filepath: /data/Banana_Linux_NoVis/Banana.x86_64
  Success: 13.0          # score success cutoff

# Parameters for the DQN Agent
Agent:
  Buffer_size: 100000    # replay buffer size
  Batch_size: 64         # minibatch size
  Gamma: 0.99            # discount factor
  Tau: 0.001              # for soft update of target parameters
  Lr: 0.0005               # learning rate
  Update_every: 4        # how often to update the network
  Brain_index: 0         # index of agent in environment

# Hyperparameters used during optimization
Training:
  Number_episodes: 2000  # Number of episodes
  Max_timesteps: 1000    # Maximum number of timesteps per episode
  Eps_start: 1.0         # Starting epsilon value for e-Greedy agent
  Eps_end:               # Minimum value for e-Greedy agent
  Eps_decay:  0.995      # How much epsilon decays during each episode
  Train_mode: True
  Score_window: 100

# Hyperparameters used to define the network architecture
Model:
  fc1_size: 100          # Dimensionality of first fully connected layer
  fc2_size: 100          # Dimensionality of second fully connected layer