req test

cnheider · cnheider · commit d3449a53d6fa · 2022-02-22T23:02:09.000+01:00
diff --git a/.github/workflows/publish-to-test-pypi.yml b/.github/workflows/publish-to-test-pypi.yml
@@ -32,18 +32,18 @@ jobs:
               .
       - name: Publish distribution 📦 to Test PyPI
         env:
-          test_pypi_password: ${{ secrets.test_pypi_password }}
-        if:   env.test_pypi_password != null && endsWith(github.ref, 'master')
+          test_pypi_password: ${{ secrets.test_pypi_secret }}
+        if:   env.test_pypi_password != null && endsWith(github.ref, 'master') && github.repository_owner == 'sintefneodroid'
         uses: pypa/gh-action-pypi-publish@master
         with:
-          password:       env.test_pypi_password
+          password:       ${{ secrets.test_pypi_secret }}
           repository_url: https://test.pypi.org/legacy/
       - name: Publish distribution 📦 to PyPI
         env:
-          pypi_password: ${{ secrets.pypi_password }}
-        if:   env.pypi_password != null && startsWith(github.ref, 'refs/tags')
+          pypi_password: ${{ secrets.pypi_secret }}
+        if:   env.pypi_password != null && startsWith(github.ref, 'refs/tags') && github.repository_owner == 'sintefneodroid'
         uses: pypa/gh-action-pypi-publish@master
         with:
-          password: ${{ secrets.pypi_password }}
+          password: ${{ secrets.pypi_secret }}
           #verbose: true
           #skip_existing: true
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303c1ac61a05e76d459f89bf7879123af4cc78b61b4a03108d5e6ef3d8c56ee7
-size 8495
+oid sha256:5684a401a5dee624290d4620ccb5366cf5cb3c2f81bff1e096ecba58e45e3bbd
+size 8699
diff --git a/neodroidagent/agents/numpy_agents/model_free/non_contextual/ucb1_policy.py b/neodroidagent/agents/numpy_agents/model_free/non_contextual/ucb1_policy.py
@@ -2,7 +2,9 @@
 # -*- coding: utf-8 -*-
 import argparse
 
-from neodroid.environments.droid_environment import SingleUnityEnvironment
+from neodroid.environments.droid_environment.unity.deprecated import (
+    SingleUnityEnvironment,
+)
 from neodroid.utilities import Displayable
 from neodroidagent.agents.numpy_agents.numpy_agent import NumpyAgent
 from neodroidagent.utilities.exploration.sampling.ucb1 import UCB1
diff --git a/neodroidagent/agents/torch_agents/model_based/README.md b/neodroidagent/agents/torch_agents/model_based/README.md
@@ -0,0 +1,2 @@
+# Model Based
+Iterate all transitions and record all values
diff --git a/neodroidagent/agents/torch_agents/model_based/__init__.py b/neodroidagent/agents/torch_agents/model_based/__init__.py
diff --git a/neodroidagent/agents/torch_agents/model_based/control/README.md b/neodroidagent/agents/torch_agents/model_based/control/README.md
@@ -0,0 +1 @@
+# Deep Model Predictive Control
diff --git a/neodroidagent/agents/torch_agents/model_based/control/__init__.py b/neodroidagent/agents/torch_agents/model_based/control/__init__.py
@@ -0,0 +1,8 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+__author__ = "heider"
+__doc__ = r"""
+
+           Created on 26/01/2022
+           """
diff --git a/neodroidagent/agents/torch_agents/model_based/control/deep_mpc.py b/neodroidagent/agents/torch_agents/model_based/control/deep_mpc.py
@@ -0,0 +1,8 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+__author__ = "heider"
+__doc__ = r"""
+
+           Created on 26/01/2022
+           """
diff --git a/neodroidagent/agents/torch_agents/model_free/README.md b/neodroidagent/agents/torch_agents/model_free/README.md
@@ -1,3 +1,5 @@
 # Model Free Agents
 
+Approximate dynamic programming
+
 - [Review](https://lilianweng.github.io/lil-log/2018/04/08/policy-gradient-algorithms.html#ppo)
diff --git a/neodroidagent/agents/torch_agents/model_free/off_policy/README.md b/neodroidagent/agents/torch_agents/model_free/off_policy/README.md
@@ -0,0 +1,2 @@
+# Off Policy
+Sometimes perform random actions (maybe suboptimal) to search space otherwise choose according to the current policy
diff --git a/neodroidagent/agents/torch_agents/model_free/on_policy/README.md b/neodroidagent/agents/torch_agents/model_free/on_policy/README.md
@@ -0,0 +1,2 @@
+# On Policy
+Always perform best actions according to the current policy
diff --git a/neodroidagent/common/architectures/distributional/categorical.py b/neodroidagent/common/architectures/distributional/categorical.py
@@ -4,6 +4,7 @@
 
 import numpy
 import torch
+import wrapt
 from torch.distributions import Categorical
 from torch.nn import functional as F
 
diff --git a/neodroidagent/common/memory/sample_transition_buffer.py b/neodroidagent/common/memory/sample_transition_buffer.py
@@ -8,7 +8,7 @@
 )
 from neodroidagent.common.memory.transitions import Transition, TransitionPoint
 from neodroidagent.utilities import NoData
-from warg.arguments import wrap_args
+from draugr.python_utilities import wrap_args
 
 __author__ = "Christian Heider Nielsen"
 __doc__ = r"""
diff --git a/neodroidagent/common/memory/trajectories/trajectory_buffer.py b/neodroidagent/common/memory/trajectories/trajectory_buffer.py
@@ -3,12 +3,13 @@
 from dataclasses import dataclass
 from typing import Any, Sequence
 
+from warg import OrdinalIndexingDictMixin, IterDictValuesMixin
+
 from neodroidagent.common.memory.data_structures.expandable_circular_buffer import (
     ExpandableCircularBuffer,
 )
 from neodroidagent.utilities import NoData
-from warg import OrdinalIndexingDictMixin, IterDictValuesMixin
-from warg.arguments import wrap_args
+from draugr.python_utilities import wrap_args
 
 __author__ = "Christian Heider Nielsen"
 
diff --git a/neodroidagent/common/memory/trajectories/transition_point_trajectory_buffer.py b/neodroidagent/common/memory/trajectories/transition_point_trajectory_buffer.py
@@ -7,7 +7,7 @@
 )
 from neodroidagent.common.memory.transitions import ValuedTransitionPoint
 from neodroidagent.utilities import NoData
-from warg.arguments import wrap_args
+from draugr.python_utilities import wrap_args
 
 __author__ = "Christian Heider Nielsen"
 __doc__ = r"""
diff --git a/neodroidagent/common/memory/transition_point_buffer.py b/neodroidagent/common/memory/transition_point_buffer.py
@@ -7,7 +7,7 @@
 )
 from neodroidagent.common.memory.transitions import TransitionPoint
 from neodroidagent.utilities import NoData
-from warg.arguments import wrap_args
+from draugr.python_utilities import wrap_args
 
 __author__ = "Christian Heider Nielsen"
 __doc__ = r"""
diff --git a/neodroidagent/common/memory/transitions/transitions.py b/neodroidagent/common/memory/transitions/transitions.py
@@ -3,12 +3,13 @@
 from typing import Any, Sequence, Sized
 
 from attr import dataclass
+from warg import OrdinalIndexingDictMixin, IterDictValuesMixin
 
 from neodroid.utilities.transformations.terminal_masking import (
     non_terminal_mask,
     non_terminal_numerical_mask,
 )
-from warg.mixins.dict_mixins import OrdinalIndexingDictMixin, IterDictValuesMixin
+
 
 __author__ = "Christian Heider Nielsen"
 
diff --git a/neodroidagent/common/session_factory/vertical/procedures/procedure_specification.py b/neodroidagent/common/session_factory/vertical/procedures/procedure_specification.py
@@ -4,10 +4,12 @@
 from pathlib import Path
 from typing import Iterable, List, Union
 
+from draugr import min_interval_wrapper_global
+
 from neodroid.environments import Environment
 from neodroidagent.agents import Agent
 from warg import drop_unused_kws
-from draugr import max_freq_wrapper_global
+
 
 __author__ = "Christian Heider Nielsen"
 __doc__ = r"""
@@ -47,7 +49,7 @@ def __init__(
         if save_best_throughout_training and train_agent:
             func = self.agent.save
             if min_save_interval:
-                max_freq_wrapper_global(func, max_freq=min_save_interval)
+                min_interval_wrapper_global(func, min_interval=min_save_interval)
             on_improvement_callbacks.append(func)
         self.on_improvement_callbacks = on_improvement_callbacks
 
diff --git a/neodroidagent/entry_points/tensorboard_entry_point.py b/neodroidagent/entry_points/tensorboard_entry_point.py
@@ -5,7 +5,7 @@
 __author__ = "Christian Heider Nielsen"
 __doc__ = ""
 
-from draugr.stopping import IgnoreInterruptSignal
+from draugr import IgnoreInterruptSignal
 
 
 def main(keep_alive=True):
diff --git a/requirements/requirements_docs.txt b/requirements/requirements_docs.txt
@@ -1,3 +1,4 @@
 sphinx
 m2r2
 sphinxcontrib-programoutput
+mistune<2.0.0
diff --git a/setup.cfg b/setup.cfg
@@ -2,7 +2,7 @@
 test = pytest
 
 [bdist_wheel]
-python-tag = py36
+python-tag = py38
 
 [metadata]
 license_file = LICENSE.md
diff --git a/setup.py b/setup.py
diff --git a/tests/req_unit_test.py b/tests/req_unit_test.py

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	`+# Model Based`
	`2`	`+Iterate all transitions and record all values`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	`+# Off Policy`
	`2`	`+Sometimes perform random actions (maybe suboptimal) to search space otherwise choose according to the current policy`