README.md

metadata

env_name: LunarLander-v3
tags:
  - LunarLander-v3
  - rainbow-dqn (with uniform sampling)
  - reinforcement-learning
  - custom-implementation
  - deep-q-learning
  - pytorch
  - rainbow
  - dqn
model-index:
  - name: Rainbow-1d-LunarLander-v3-NoPer
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: LunarLander-v3
          type: LunarLander-v3
        metrics:
          - type: mean_reward
            value: 282.11 +/- 19.77
            name: mean_reward
            verified: false

Rainbow-DQN (with uniform sampling) Agent playing LunarLander-v3

This is a trained model of a Rainbow-DQN (with uniform sampling) agent playing LunarLander-v3.

Usage

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

conda create -n drl python=3.12
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/Rainbow-1d-LunarLander-v3-NoPer", 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.