Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

hw_submission(吴振锋):add hw6_20230517 #76

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

hw_submission(吴振锋):add hw6_20230517 #76

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
204 changes: 204 additions & 0 deletions chapter6_marl/environment.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,204 @@
name: opendilab
channels:
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/r
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/msys2
- defaults
dependencies:
- _libgcc_mutex=0.1=main
- _openmp_mutex=5.1=1_gnu
- ca-certificates=2022.10.11=h06a4308_0
- certifi=2022.12.7=py39h06a4308_0
- ld_impl_linux-64=2.38=h1181459_1
- libffi=3.3=he6710b0_2
- libgcc-ng=11.2.0=h1234567_1
- libgomp=11.2.0=h1234567_1
- libstdcxx-ng=11.2.0=h1234567_1
- ncurses=6.3=h5eee18b_3
- openssl=1.1.1s=h7f8727e_0
- pip=22.3.1=py39h06a4308_0
- python=3.9.0=hdb3f193_2
- readline=8.2=h5eee18b_0
- setuptools=65.6.3=py39h06a4308_0
- sqlite=3.40.1=h5082296_0
- tk=8.6.12=h1ccaba5_0
- tzdata=2022g=h04d1e81_0
- wheel=0.37.1=pyhd3eb1b0_0
- xz=5.2.8=h5eee18b_0
- zlib=1.2.13=h5eee18b_0
- pip:
- absl-py==1.4.0
- ale-py==0.7.5
- appdirs==1.4.4
- async-timeout==4.0.2
- attrs==22.2.0
- autorom==0.6.1
- blinker==1.6.2
- box2d==2.3.2
- box2d-kengz==2.3.3
- box2d-py==2.3.5
- bsuite==0.3.5
- cffi==1.15.1
- charset-normalizer==3.0.1
- click==7.1.2
- cloudpickle==1.6.0
- cmake==3.26.3
- commonmark==0.9.1
- contourpy==1.0.7
- cycler==0.11.0
- cython==0.29.33
- decorator==5.1.1
- di-engine==0.4.7
- di-toolkit==0.1.0
- di-treetensor==0.4.0
- dill==0.3.6
- dm-env==1.6
- dm-tree==0.1.8
- docker-pycreds==0.4.0
- easydict==1.9
- enum-tools==0.9.0.post1
- evogym==1.0.0
- exceptiongroup==1.1.0
- fasteners==0.18
- filelock==3.9.0
- flake8==6.0.0
- flask==1.1.4
- fonttools==4.38.0
- frozendict==2.3.7
- gitdb==4.0.10
- gitpython==3.1.30
- glcontext==2.3.7
- glfw==2.5.6
- gpy==1.10.0
- gpyopt==1.2.6
- gym==0.25.1
- gym-notices==0.0.8
- gym-super-mario-bros==7.4.0
- gym3==0.3.3
- gymnasium==0.27.1
- gymnasium-notices==0.0.1
- h5py==3.7.0
- hanabi-learning-environment==0.0.1
- hbutils==0.8.0
- hickle==5.0.2
- idna==3.4
- imageio==2.25.1
- imageio-ffmpeg==0.3.0
- importlib-metadata==4.13.0
- importlib-resources==5.12.0
- inflect==6.0.2
- iniconfig==2.0.0
- itsdangerous==1.1.0
- jax-jumpy==0.2.0
- jinja2==2.11.3
- joblib==1.2.0
- kiwisolver==1.4.4
- lazy-loader==0.2
- llvmlite==0.39.1
- lxml==4.9.2
- lz4==4.3.2
- magent==0.1.14
- mamujoco==1.1.0
- markupsafe==2.0.1
- matplotlib==3.6.3
- mccabe==0.7.0
- metadrive-simulator==0.2.6.0
- minigrid==2.1.1
- mizani==0.8.1
- moderngl==5.7.4
- mpire==2.6.0
- mujoco==2.2.0
- mujoco-py==2.1.2.14
- multi-agent-ale-py==0.1.11
- neat-python==0.92
- nes-py==8.2.1
- networkx==3.1
- numba==0.56.4
- numpy==1.23.5
- nvidia-cublas-cu11==11.10.3.66
- nvidia-cuda-nvrtc-cu11==11.7.99
- nvidia-cuda-runtime-cu11==11.7.99
- nvidia-cudnn-cu11==8.5.0.96
- opencv-python==4.7.0.68
- opencv-python-headless==4.7.0.72
- packaging==23.0
- palettable==3.3.1
- panda3d==1.10.8
- panda3d-gltf==0.13
- panda3d-simplepbr==0.10
- pandas==1.5.2
- paramz==0.9.5
- pathtools==0.1.2
- patsy==0.5.3
- pettingzoo==1.12.0
- pillow==9.4.0
- plotnine==0.10.1
- pluggy==1.0.0
- procgen==0.10.7
- protobuf==3.20.1
- psutil==5.9.4
- py==1.11.0
- pybind11==2.10.3
- pycodestyle==2.10.0
- pycparser==2.21
- pydantic==1.10.4
- pyflakes==3.0.1
- pygame==2.0.0
- pygifsicle==1.0.7
- pyglet==1.5.21
- pygments==2.14.0
- pymunk==6.2.0
- pynng==0.7.2
- pyopengl==3.1.6
- pyopengl-accelerate==3.1.6
- pyparsing==3.0.9
- pytest==7.0.1
- python-chess==0.31.4
- python-dateutil==2.8.2
- python-graphviz==0.20.1
- pytz==2022.7.1
- pywavelets==1.4.1
- pyyaml==6.0
- readerwriterlock==1.0.9
- redis==4.4.2
- requests==2.28.2
- responses==0.12.1
- rich==13.1.0
- rlcard==1.0.4
- rocket-recycling==0.1
- scikit-image==0.20.0
- scikit-learn==1.2.0
- scipy==1.9.1
- seaborn==0.12.2
- sentry-sdk==1.13.0
- setproctitle==1.3.2
- six==1.16.0
- smmap==5.0.0
- sniffio==1.3.0
- stable-baselines3==1.7.0
- statsmodels==0.13.5
- support-developer==1.0.5
- swig==4.1.1
- tabulate==0.9.0
- tensorboardx==2.5.1
- termcolor==2.2.0
- threadpoolctl==3.1.0
- tifffile==2023.3.21
- tomli==2.0.1
- torch==1.12.0
- torchvision==0.14.1
- tqdm==4.64.1
- treevalue==1.4.3
- trueskill==0.4.5
- ttkbootstrap==1.10.1
- typing==3.7.4.3
- typing-extensions==4.4.0
- urllib3==1.26.14
- urlobject==2.4.3
- wandb==0.13.9
- werkzeug==1.0.1
- yapf==0.29.0
- zipp==3.11.0
prefix: /home/polarstar/miniconda3/envs/opendilab
Binary file added chapter6_marl/multi_mujoco_ant_2x4_ppo/ckpt/ckpt_best.pth.tar
View file
Open in desktop
Binary file not shown.
Binary file added chapter6_marl/multi_mujoco_ant_2x4_ppo/ckpt/iteration_0.pth.tar
View file
Open in desktop
Binary file not shown.
Binary file added chapter6_marl/multi_mujoco_ant_2x4_ppo/ckpt/iteration_10000.pth.tar
View file
Open in desktop
Binary file not shown.
Binary file added chapter6_marl/multi_mujoco_ant_2x4_ppo/ckpt/iteration_20000.pth.tar
View file
Open in desktop
Binary file not shown.
Binary file added chapter6_marl/multi_mujoco_ant_2x4_ppo/ckpt/iteration_28668.pth.tar
View file
Open in desktop
Binary file not shown.
154 changes: 154 additions & 0 deletions chapter6_marl/multi_mujoco_ant_2x4_ppo/formatted_total_config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,154 @@
from easydict import EasyDict

main_config = dict(
exp_name='multi_mujoco_ant_2x4_ppo',
env=dict(
manager=dict(
episode_num=float('inf'),
max_retry=5,
step_timeout=None,
auto_reset=True,
reset_timeout=None,
retry_type='reset',
retry_waiting_time=0.1,
shared_memory=True,
copy_on_get=True,
context='fork',
wait_num=float('inf'),
step_wait_timeout=None,
connect_timeout=60,
reset_inplace=False,
cfg_type='SyncSubprocessEnvManagerDict',
type='subprocess',
),
stop_value=6000,
n_evaluator_episode=8,
scenario='Ant-v2',
agent_conf='2x4d',
agent_obsk=2,
add_agent_id=False,
episode_limit=1000,
collector_env_num=8,
evaluator_env_num=8,
),
policy=dict(
model=dict(
agent_num=2,
agent_obs_shape=54,
global_obs_shape=111,
action_shape=4,
action_space='continuous',
),
learn=dict(
learner=dict(
train_iterations=1000000000,
dataloader=dict(
num_workers=0,
),
log_policy=True,
hook=dict(
load_ckpt_before_run='',
log_show_after_iter=100,
save_ckpt_after_iter=10000,
save_ckpt_after_run=True,
),
cfg_type='BaseLearnerDict',
),
epoch_per_collect=3,
batch_size=800,
learning_rate=0.0005,
value_weight=0.5,
entropy_weight=0.001,
clip_ratio=0.2,
adv_norm=True,
value_norm=True,
ppo_param_init=True,
grad_clip_type='clip_norm',
grad_clip_value=5,
ignore_done=False,
),
collect=dict(
collector=dict(
deepcopy_obs=False,
transform_obs=False,
collect_print_freq=100,
cfg_type='SampleSerialCollectorDict',
type='sample',
),
unroll_len=1,
discount_factor=0.99,
gae_lambda=0.95,
env_num=8,
n_sample=3200,
),
eval=dict(
evaluator=dict(
eval_freq=1000,
render={'render_freq': -1, 'mode': 'train_iter'},
cfg_type='InteractionSerialEvaluatorDict',
stop_value=6000,
n_episode=8,
),
env_num=8,
),
other=dict(
replay_buffer=dict(
type='advanced',
replay_buffer_size=4096,
max_use=float('inf'),
max_staleness=float('inf'),
alpha=0.6,
beta=0.4,
anneal_step=100000,
enable_track_used_data=False,
deepcopy=False,
thruput_controller=dict(
push_sample_rate_limit=dict(
max=float('inf'),
min=0,
),
window_seconds=30,
sample_min_limit_ratio=1,
),
monitor=dict(
sampled_data_attr=dict(
average_range=5,
print_freq=200,
),
periodic_thruput=dict(
seconds=60,
),
),
cfg_type='AdvancedReplayBufferDict',
),
),
on_policy=True,
cuda=True,
multi_gpu=False,
bp_update_sync=True,
traj_len_inf=False,
priority=False,
priority_IS_weight=False,
recompute_adv=True,
action_space='continuous',
nstep_return=False,
multi_agent=True,
transition_with_policy_data=True,
cfg_type='PPOCommandModePolicyDict',
),
)
main_config = EasyDict(main_config)
main_config = main_config
create_config = dict(
env=dict(
type='mujoco_multi',
import_names=['dizoo.multiagent_mujoco.envs.multi_mujoco_env'],
),
env_manager=dict(
cfg_type='SyncSubprocessEnvManagerDict',
type='subprocess',
),
policy=dict(type='ppo'),
)
create_config = EasyDict(create_config)
create_config = create_config
Empty file added chapter6_marl/multi_mujoco_ant_2x4_ppo/git_diff.txt
View file
Open in desktop
Empty file.
Loading