Skip to content

Merge Experimental into master #10

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.

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

Merged
merged 2 commits into from
Jun 7, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .pep8
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
[pycodestyle]
max_line_length = 127
51 changes: 26 additions & 25 deletions default_config.py
Original file line number Diff line number Diff line change
@@ -1,37 +1,38 @@
from collections import OrderedDict
from mdp_playground.config_processor import *

timesteps_total = 10_000
num_seeds = 3
from collections import OrderedDict
var_env_configs = OrderedDict({
'state_space_size': [8],#, 10, 12, 14] # [2**i for i in range(1,6)]
'action_space_size': [8],#2, 4, 8, 16] # [2**i for i in range(1,6)]
'delay': [0] + [2**i for i in range(4)],
'sequence_length': [1, 2, 3, 4],#i for i in range(1,4)]
'reward_density': [0.25], # np.linspace(0.0, 1.0, num=5)
'make_denser': [False],
'terminal_state_density': [0.25], # np.linspace(0.1, 1.0, num=5)
'transition_noise': [0],#, 0.01, 0.02, 0.10, 0.25]
'reward_noise': [0],#, 1, 5, 10, 25] # Std dev. of normal dist.
# 'reward_scale': [10.0],
'dummy_seed': [i for i in range(num_seeds)],
})

var_configs = OrderedDict({
"env": var_env_configs
})
var_env_configs = OrderedDict(
{
"state_space_size": [8], # , 10, 12, 14] # [2**i for i in range(1,6)]
"action_space_size": [8], # 2, 4, 8, 16] # [2**i for i in range(1,6)]
"delay": [0] + [2 ** i for i in range(4)],
"sequence_length": [1, 2, 3, 4], # i for i in range(1,4)]
"reward_density": [0.25], # np.linspace(0.0, 1.0, num=5)
"make_denser": [False],
"terminal_state_density": [0.25], # np.linspace(0.1, 1.0, num=5)
"transition_noise": [0], # , 0.01, 0.02, 0.10, 0.25]
"reward_noise": [0], # , 1, 5, 10, 25] # Std dev. of normal dist.
# 'reward_scale': [10.0],
"dummy_seed": [i for i in range(num_seeds)],
}
)

var_configs = OrderedDict({"env": var_env_configs})

env_config = {
"env": "RLToy-v0",
"horizon": 100,
"env_config": {
'seed': 0, #seed
'state_space_type': 'discrete',
'action_space_type': 'discrete',
'generate_random_mdp': True,
'repeats_in_sequences': False,
'reward_scale': 1.0,
'completely_connected': True,
"seed": 0, # seed
"state_space_type": "discrete",
"action_space_type": "discrete",
"generate_random_mdp": True,
"repeats_in_sequences": False,
"reward_scale": 1.0,
"completely_connected": True,
},
}

Expand All @@ -49,7 +50,7 @@
"final_prioritized_replay_beta": 1.0,
"hiddens": None,
"learning_starts": 1000,
"lr": 1e-4, # "lr": grid_search([1e-2, 1e-4, 1e-6]),
"lr": 1e-4, # "lr": grid_search([1e-2, 1e-4, 1e-6]),
"n_step": 1,
"noisy": False,
"num_atoms": 1,
Expand Down
26 changes: 13 additions & 13 deletions docs/conf.py
Original file line number Diff line number Diff line change
Expand Up @@ -13,18 +13,18 @@
import os
import sys

sys.path.insert(0, os.path.abspath('..'))
sys.path.append(os.path.abspath('../mdp_playground'))
sys.path.insert(0, os.path.abspath(".."))
sys.path.append(os.path.abspath("../mdp_playground"))

# -- Project information -----------------------------------------------------

# TODO: read automatically from setup
project = 'MDP Playground'
copyright = '2021, MDP Playground developers'
author = 'MDP Playground developers'
project = "MDP Playground"
copyright = "2021, MDP Playground developers"
author = "MDP Playground developers"

# The full version, including alpha/beta/rc tags
release = '0.0.1'
release = "0.0.1"


# -- General configuration ---------------------------------------------------
Expand All @@ -33,11 +33,11 @@
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
# ones.
extensions = [
'sphinx.ext.autodoc',
'sphinx.ext.napoleon',
'sphinx.ext.coverage',
"sphinx.ext.autodoc",
"sphinx.ext.napoleon",
"sphinx.ext.coverage",
"sphinx.ext.viewcode",
'sphinx.ext.autosummary',
"sphinx.ext.autosummary",
]

napoleon_google_docstring = False
Expand All @@ -50,12 +50,12 @@
autodoc_inherit_docstrings = True # If no docstring, inherit from base class

# Add any paths that contain templates here, relative to this directory.
templates_path = ['_templates']
templates_path = ["_templates"]

# List of patterns, relative to source directory, that match files and
# directories to ignore when looking for source files.
# This pattern also affects html_static_path and html_extra_path.
exclude_patterns = ['_build', '_templates', 'Thumbs.db', '.DS_Store']
exclude_patterns = ["_build", "_templates", "Thumbs.db", ".DS_Store"]


# -- Options for HTML output -------------------------------------------------
Expand All @@ -68,4 +68,4 @@
# Add any paths that contain custom static files (such as style sheets) here,
# relative to this directory. They are copied after the builtin static files,
# so a file named "default.css" will overwrite the builtin "default.css".
html_static_path = ['_static']
html_static_path = ["_static"]
Loading