metadata
tags:
- FrozenLake-v1-4x4
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-learning-FrozenLake-v1-4x4-slippery-params-v3
results:
- metrics:
- type: mean_reward
value: 0.90 +/- 0.30
name: mean_reward
task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4
type: FrozenLake-v1-4x4
Q-Learning Agent playing FrozenLake-v1-4x4-slippery
This is a trained model of a Q-Learning agent playing FrozenLake-v1-4x4-slippery .
Usage
model = load_from_hub(repo_id="linker81/q-learning-FrozenLake-v1-4x4-slippery-params-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
evaluate_agent(env, model["max_steps"], model["n_eval_episodes"], model["qtable"], model["eval_seed"])