TD3-Walker2dV5 / README.md
winkin119's picture
upload via upload_folder 2025-08-05T09:49:11.989523+00:00
50d0a2b verified
metadata
env_name: Walker2d-v5
tags:
  - Walker2d-v5
  - td3
  - reinforcement-learning
  - custom-implementation
  - policy-gradient
  - pytorch
  - ddpg
model-index:
  - name: TD3-Walker2dV5
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: Walker2d-v5
          type: Walker2d-v5
        metrics:
          - type: mean_reward
            value: 4348.91 +/- 73.32
            name: mean_reward
            verified: false

TD3 Agent playing Walker2d-v5

This is a trained model of a TD3 agent playing Walker2d-v5.

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/TD3-Walker2dV5", filename="full_model.pt")

# Create the environment. 
env = gym.make("Walker2d-v5")
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.