A3C-LunarLanderV3 / README.md
winkin119's picture
upload via upload_folder 2025-08-04T13:41:58.009287+00:00
46408f1 verified
metadata
env_name: LunarLander-v3
tags:
  - LunarLander-v3
  - a3c
  - reinforcement-learning
  - custom-implementation
  - policy-gradient
  - pytorch
  - a3c
  - gae
model-index:
  - name: A3C-LunarLanderV3
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: LunarLander-v3
          type: LunarLander-v3
        metrics:
          - type: mean_reward
            value: 258.83 +/- 17.21
            name: mean_reward
            verified: false

A3C Agent playing LunarLander-v3

This is a trained model of a A3C agent playing LunarLander-v3.

Usage

create the conda env in https://github.com/GeneHit/drl_practice

conda create -n drl python=3.10
conda activate drl
python -m pip install -r requirements.txt

play with full model

# load the full model
model = load_from_hub(repo_id="winkin119/A3C-LunarLanderV3", filename="full_model.pt")

# Create the environment. 
env = gym.make("LunarLander-v3")
state, _ = env.reset()
action = model.action(state)
...

There is also a state dict version of the model, you can check the corresponding definition in the repo.