metadata
env_name: Pendulum-v1
tags:
- Pendulum-v1
- sac
- reinforcement-learning
- custom-implementation
- policy-gradient
- pytorch
- ddpg
model-index:
- name: SAC-PendulumV1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pendulum-v1
type: Pendulum-v1
metrics:
- type: mean_reward
value: '-129.63 +/- 63.60'
name: mean_reward
verified: false
SAC Agent playing Pendulum-v1
This is a trained model of a SAC agent playing Pendulum-v1.
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/SAC-PendulumV1", filename="full_model.pt")
# Create the environment.
env = gym.make("Pendulum-v1")
state, _ = env.reset()
action = model.action(state)
...
There is also a state dict version of the model.