DQN Agent playing CartPole-v1

This is a trained model of a DQN agent playing CartPole-v1
using the stable-baselines3 library
and the RL Zoo.
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.

Usage (with SB3 RL Zoo)

RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo
SB3: https://github.com/DLR-RM/stable-baselines3
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
# Download model and save it into the logs/ folder<br /> python -m rl_zoo3.load_from_hub --algo dqn --env CartPole-v1 -orga sb3 -f logs/<br /> python enjoy.py --algo dqn --env CartPole-v1 -f logs/<br />

Training (with the RL Zoo)

python train.py --algo dqn --env CartPole-v1 -f logs/<br /> # Upload the model and generate video (when possible)<br /> python -m rl_zoo3.push_to_hub --algo dqn --env CartPole-v1 -f logs/ -orga sb3<br />

Hyperparameters

OrderedDict([('batch_size', 64),<br /> ('buffer_size', 100000),<br /> ('exploration_final_eps', 0.04),<br /> ('exploration_fraction', 0.16),<br /> ('gamma', 0.99),<br /> ('gradient_steps', 128),<br /> ('learning_rate', 0.0023),<br /> ('learning_starts', 1000),<br /> ('n_timesteps', 50000.0),<br /> ('policy', 'MlpPolicy'),<br /> ('policy_kwargs', 'dict(net_arch=[256, 256])'),<br /> ('target_update_interval', 10),<br /> ('train_freq', 256),<br /> ('normalize', False)])<br />