A2C Agent playing PandaReachDense-v2
This is a trained model of a A2C agent playing PandaReachDense-v2 using the stable-baselines3 library.
Usage (with Stable-baselines3)
import pybullet_envs
import panda_gym
import gym
import os
from huggingface_sb3 import load_from_hub, package_to_hub
from stable_baselines3 import A2C
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
from stable_baselines3.common.env_util import make_vec_env
from huggingface_hub import notebook_login
load_model = load_from_hub(
repo_id="kinkpunk/a2c-PandaReachDense-v2",
filename="a2c-PandaReachDense-v2.zip",
)
model = A2C.load(load_model)
Panda Gym environments: arxiv.org/abs/2106.13687
- Downloads last month
- 2
Evaluation results
- mean_reward on PandaReachDense-v2self-reported-1.65 +/- 0.14