Play LunarLander-v2 with A2C Policy
Model Description
This is a simple A2C implementation to OpenAI/Gym/Box2d LunarLander-v2 using the DI-engine library and the DI-zoo.
DI-engine is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported by reusing different abstraction levels of DI-engine reinforcement learning framework.
Model Usage
Install the Dependencies
(Click for Details)
# install huggingface_ding
git clone https://github.com/opendilab/huggingface_ding.git
pip3 install -e ./huggingface_ding/
# install environment dependencies if needed
pip3 install DI-engine[common_env]
Git Clone from Huggingface and Run the Model
(Click for Details)
# running with trained model
python3 -u run.py
run.py
from ding.bonus import A2CAgent
from ding.config import Config
from easydict import EasyDict
import torch
policy_state_dict = torch.load("pytorch_model.bin", map_location=torch.device("cpu"))
cfg = EasyDict(Config.file_to_dict("policy_config.py"))
agent = A2CAgent(
env="lunarlander_discrete", exp_name="Lunarlander-v2-A2C", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
agent.train(step=5000)
agent.deploy(enable_save_replay=True)
Run Model by Using Huggingface_ding
(Click for Details)
# running with trained model
python3 -u run.py
run.py
from ding.bonus import A2CAgent
from huggingface_ding import pull_model_from_hub
policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/Lunarlander-v2-A2C")
agent = A2CAgent(
env="lunarlander_discrete", exp_name="Lunarlander-v2-A2C", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
agent.train(step=5000)
agent.deploy(enable_save_replay=True)
Model Training
Train the Model and Push to Huggingface_hub
(Click for Details)
#Training Your Own Agent
python3 -u train.py
train.py
from ding.bonus import A2CAgent
from huggingface_ding import push_model_to_hub
agent = A2CAgent(env="lunarlander_discrete", exp_name="Lunarlander-v2-A2C")
return_ = agent.train(step=int(20000000), collector_env_num=8, evaluator_env_num=8, debug=False)
push_model_to_hub(
agent=agent.best,
env_name="OpenAI/Gym/Box2d",
task_name="LunarLander-v2",
algo_name="A2C",
wandb_url=return_.wandb_url,
github_repo_url="https://github.com/opendilab/DI-engine",
github_doc_model_url="https://di-engine-docs.readthedocs.io/en/latest/12_policies/a2c.html",
github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/lunarlander.html",
installation_guide="pip3 install DI-engine[common_env]",
usage_file_by_git_clone="./a2c/lunarlander_a2c_deploy.py",
usage_file_by_huggingface_ding="./a2c/lunarlander_a2c_download.py",
train_file="./a2c/lunarlander_a2c.py",
repo_id="OpenDILabCommunity/Lunarlander-v2-A2C"
)
Configuration
(Click for Details)
exp_config = {
'env': {
'manager': {
'episode_num': float("inf"),
'max_retry': 1,
'retry_type': 'reset',
'auto_reset': True,
'step_timeout': None,
'reset_timeout': None,
'retry_waiting_time': 0.1,
'cfg_type': 'BaseEnvManagerDict'
},
'stop_value': 240,
'collector_env_num': 8,
'evaluator_env_num': 8,
'env_id': 'LunarLander-v2',
'n_evaluator_episode': 8
},
'policy': {
'model': {
'obs_shape': 8,
'action_shape': 4
},
'learn': {
'learner': {
'train_iterations': 1000000000,
'dataloader': {
'num_workers': 0
},
'log_policy': True,
'hook': {
'load_ckpt_before_run': '',
'log_show_after_iter': 100,
'save_ckpt_after_iter': 10000,
'save_ckpt_after_run': True
},
'cfg_type': 'BaseLearnerDict'
},
'update_per_collect': 1,
'batch_size': 160,
'learning_rate': 0.0003,
'betas': [0.9, 0.999],
'eps': 1e-08,
'grad_norm': 0.5,
'value_weight': 0.5,
'entropy_weight': 0.001,
'adv_norm': True,
'ignore_done': False
},
'collect': {
'collector': {},
'unroll_len': 1,
'discount_factor': 0.99,
'gae_lambda': 0.95,
'n_sample': 320
},
'eval': {
'evaluator': {
'eval_freq': 1000,
'render': {
'render_freq': -1,
'mode': 'train_iter'
},
'cfg_type': 'InteractionSerialEvaluatorDict',
'n_episode': 8,
'stop_value': 240
}
},
'other': {
'replay_buffer': {}
},
'on_policy': True,
'cuda': True,
'multi_gpu': False,
'bp_update_sync': True,
'traj_len_inf': False,
'type': 'a2c',
'priority': False,
'priority_IS_weight': False,
'cfg_type': 'A2CPolicyDict'
},
'exp_name': 'Lunarlander-v2-A2C',
'wandb_logger': {
'gradient_logger': True,
'video_logger': True,
'plot_logger': True,
'action_logger': True,
'return_logger': False
},
'seed': 0
}
Training Procedure
Model Information
Environments
