You can deploy this model and start earning money today!

MattStammers/
tqc-BipedalWalkerHardcore-v3

Name: tqc-BipedalWalkerHardcore-v3
Availability: InStock

stable-baselines3

BipedalWalkerHardcore-v3

deep-reinforcement-learning

reinforcement-learning

model-index

Views

No views yet

TQC Agent playing BipedalWalkerHardcore-v3

This is a trained model of a TQC agent playing BipedalWalkerHardcore-v3 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

Install the RL Zoo (with SB3 and SB3-Contrib):

pip install rl_zoo3

# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo tqc --env BipedalWalkerHardcore-v3 -orga MattStammers -f logs/
python -m rl_zoo3.enjoy --algo tqc --env BipedalWalkerHardcore-v3  -f logs/

If you installed the RL Zoo3 via pip (pip install rl_zoo3), from anywhere you can do:

python -m rl_zoo3.load_from_hub --algo tqc --env BipedalWalkerHardcore-v3 -orga MattStammers -f logs/
python -m rl_zoo3.enjoy --algo tqc --env BipedalWalkerHardcore-v3  -f logs/

Training (with the RL Zoo)

python -m rl_zoo3.train --algo tqc --env BipedalWalkerHardcore-v3 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo tqc --env BipedalWalkerHardcore-v3 -f logs/ -orga MattStammers

Hyperparameters

python

OrderedDict([('batch_size', 256),
             ('buffer_size', 1000000),
             ('ent_coef', 'auto'),
             ('gamma', 0.99),
             ('gradient_steps', 1),
             ('learning_rate', 'lin_7.3e-4'),
             ('learning_starts', 10000),
             ('n_timesteps', 2000000.0),
             ('policy', 'MlpPolicy'),
             ('policy_kwargs', 'dict(net_arch=[400, 300])'),
             ('tau', 0.01),
             ('train_freq', 1),
             ('normalize', False)])

Environment Arguments

{'render_mode': 'rgb_array'}

This was my 6th attempt to crack this. I know it can be done with TD3 and SAC but not using sb3's basic implementation as I found out when I tried. Only the sb3 TQC implementation works

MattStammers/tqc-BipedalWalkerHardcore-v3