|
--- |
|
tags: |
|
- SpaceInvaders-v4 |
|
- ppo |
|
- deep-reinforcement-learning |
|
- reinforcement-learning |
|
- custom-implementation |
|
- deep-rl-course |
|
model-index: |
|
- name: SARSA_QLEARNING |
|
results: |
|
- task: |
|
type: reinforcement-learning |
|
name: reinforcement-learning |
|
dataset: |
|
name: SpaceInvaders-v4 |
|
type: SpaceInvaders-v4 |
|
metrics: |
|
- type: mean_reward |
|
value: 4.80 +/- 6.08 |
|
name: mean_reward |
|
verified: false |
|
--- |
|
|
|
# QLEARNING_SARSA Agent Playing SpaceInvaders-v4 |
|
|
|
This is a trained model of a expected SARSA agent playing SpaceInvaders-v4. |
|
|
|
# Hyperparameters |
|
|
