Edit model card

DQN Agent Playing SpaceInvadersNoFrameskip-v4

This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4. To learn to use this model and train yours check Unit 3 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit3/introduction

Hyperparameters

{'batch_size': 32,
 'buffer_size': 200000,
 'end_e': 0.01,
 'exploration_fraction': 0.1,
 'gamma': 0.99,
 'learning_rate': 0.0001,
 'learning_starts': 80000,
 'start_e': 1.0,
 'target_network_frequency': 1000,
 'tau': 1.0,
 'total_timesteps': 2500000,
 'train_frequency': 4}
Downloads last month
0
Video Preview
loading

Evaluation results

  • mean_reward on SpaceInvadersNoFrameskip-v4
    self-reported
    729.00 +/- 268.98