saferl-lite 0.1.0__tar.gz → 0.1.2__tar.gz

saferl_lite-0.1.2/PKG-INFO

@@ -0,0 +1,239 @@
+Metadata-Version: 2.4
+Name: saferl-lite
+Version: 0.1.2
+Summary: A lightweight, explainable, and constrained reinforcement learning toolkit.
+Home-page: https://github.com/satyamcser/saferl-lite
+Author: Satyam Mishra
+Author-email: satyam@example.com
+Project-URL: Documentation, https://github.com/satyamcser/saferl-lite/tree/main/docs
+Project-URL: Source, https://github.com/satyamcser/saferl-lite
+Project-URL: Bug Tracker, https://github.com/satyamcser/saferl-lite/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: gym
+Requires-Dist: gymnasium
+Requires-Dist: numpy
+Requires-Dist: torch
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: pre-commit
+Requires-Dist: flake8
+Requires-Dist: pyyaml
+Requires-Dist: shap
+Requires-Dist: captum
+Requires-Dist: typer
+Requires-Dist: scikit-learn
+Requires-Dist: pandas
+Requires-Dist: pytest
+Requires-Dist: pytest-cov
+Requires-Dist: coverage
+Requires-Dist: mkdocs
+Requires-Dist: wandb
+Requires-Dist: mkdocs>=1.5
+Requires-Dist: mkdocs-material>=9.5
+Requires-Dist: mkdocstrings[python]
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# 🔐 SafeRL-Lite
+
+A **lightweight, explainable, and modular** Python library for **Constrained Reinforcement Learning (Safe RL)** with real-time **SHAP & saliency-based explainability**, custom metrics, and Gym-compatible wrappers.
+
+By: 
+- Satyam Mishra, Vision Mentors Ltd., Hanoi, Vietnam
+- Shivam Mishra, Phung Thao Vi, Vietnam National University, Hanoi, Vietnam
+- Dr. Vishwanath Bijalwan, SR University, Warangal, India
+- Dr. Vijay Bhaskar Semwal, MANIT, Bhopal, India
+- University of West London, London, UK
+
+<p align="center">
+  <a href="https://github.com/satyamcser/saferl-lite/blob/main/LICENSE">
+    <img src="https://img.shields.io/github/license/satyamcser/saferl-lite?style=flat-square" alt="License">
+  </a>
+  <a href="https://github.com/satyamcser/saferl-lite/stargazers">
+    <img src="https://img.shields.io/github/stars/satyamcser/saferl-lite?style=flat-square" alt="Stars">
+  </a>
+  <a href="https://pypi.org/project/saferl-lite/">
+    <img src="https://img.shields.io/pypi/v/saferl-lite?style=flat-square" alt="PyPI version">
+  </a>
+  <a href="https://github.com/satyamcser/saferl-lite/actions/workflows/ci.yml">
+    <img src="https://img.shields.io/github/actions/workflow/status/satyamcser/saferl-lite/ci.yml?branch=main&style=flat-square" alt="Build Status">
+  </a>
+</p>
+
+
+---
+
+## 🌟 Overview
+
+**SafeRL-Lite** empowers reinforcement learning agents to act under **safety constraints**, while remaining **interpretable** and **modular** for fast experimentation. It wraps standard Gym environments and DQN-based agents with:
+
+- ✅ Safety constraint logic
+- 🔍 Visual explainability (SHAP, saliency maps)
+- 📊 Violation and reward tracking
+- 🧪 Built-in testing and evaluations
+
+---
+
+## ✅ Problem We Solved
+
+Modern Reinforcement Learning (RL) agents are powerful but unsafe and opaque:
+
+- 🚫 They frequently violate safety constraints during learning or deployment (e.g., fall off a cliff in navigation tasks).
+
+- 😕 Their decision-making is a black box: humans can’t understand why a certain action was chosen.
+
+- 🔍 Standard RL libraries lack native support for:
+
+  - Enforcing hard constraints during training.
+
+  - Explaining decisions using methods like SHAP or saliency maps.
+
+## ✅ Our Solution
+SafeRL-Lite is a lightweight Python library that:
+
+1. 📏 Adds a SafetyWrapper around any Gym environment to enforce safety constraints (e.g., bounding actions, limiting states).
+
+2. 🧠 Integrates explainability methods:
+
+  - SHAPExplainer (model-agnostic local explanations).
+
+  - SaliencyExplainer (gradient-based sensitivity maps).
+
+3. 🔧 Wraps Constrained DQNs with ease, enabling safety-compliant Q-learning.
+
+4. 📊 Offers built-in metrics like violation count and safe episode tracking.
+
+## ✅ Novelty
+While Safe RL and Explainable RL are separately studied, no prior lightweight library:
+
+- Combines hard safety constraints with post-hoc interpretability.
+
+- Is designed to be minimal, pluggable, and easily installable (pip install saferl-lite) for education, experimentation, or safe deployment.
+
+- Enables real-time SHAP or saliency visualization for Gym-based agents out-of-the-box.
+``` bash
+SafeRL-Lite is the first minimal library to unify constraint satisfaction and explainability in reinforcement learning — without heavy dependencies or overhead.
+```
+
+## ✅ Our Contribution
+1. 🔐 Constraint Wrapper API: Drop-in Gym wrapper for defining and enforcing logical constraints on observations, actions, and reward signals.
+
+2. 🧠 Explainability Modules: Plug-and-play SHAP and saliency explainer classes for deep Q-networks.
+
+3. 📦 PyPI-Ready Toolkit: Easily installed, documented, and CI/CD tested; built for research and reproducibility.
+
+4. 📈 Metrics for Constraint Violation: Tracks unsafe episodes, per-step violations, and integrates cleanly with WandB or TensorBoard.
+
+## ✅ Technical Explanation
+- We define a custom SafeEnvWrapper(gym.Env) that:
+
+  - Intercepts actions.
+
+  - Applies logical rules or thresholding.
+
+  - Optionally overrides rewards or terminations if constraints are violated.
+
+- A ConstrainedDQNAgent uses:
+
+  - Safety-wrapped Gym envs.
+
+  - Standard Q-learning with optional penalty_on_violation flag.
+
+- Post-training, the SHAPExplainer and SaliencyExplainer:
+
+  - Generate local attributions using input perturbations or gradient norms.
+
+  - Can visualize per-state or per-action explanations.
+
+
+
+## ✅ Satyam's Explanation
+```bash
+Imagine you're teaching a robot to walk — but there’s lava on the floor!
+You don’t just want it to learn fast, you want it to stay safe and explain why it stepped left, not right.
+```
+SafeRL-Lite is like a safety helmet and voicebox for robots:
+
+- The helmet makes sure they don’t do dangerous stuff.
+
+- The voicebox lets them say why they made that move.
+
+## 🔧 Installation
+
+> 📦 PyPI 
+```bash
+pip install saferl-lite
+```
+
+## 🛠️ From source:
+
+```bash
+git clone https://github.com/satyamcser/saferl-lite.git
+cd saferl-lite
+pip install -e .
+```
+
+## 🚀 Quickstart
+Train a constrained DQN agent with saliency-based explainability:
+
+```bash
+python train.py --env CartPole-v1 --constraint pole_angle --explain shap
+```
+
+🔹 This:
+
+- Adds a pole-angle constraint wrapper to the Gym env
+
+- Logs violations
+
+- Displays SHAP or saliency explanations for agent decisions
+
+## 🧠 Features
+#### ✅ Constrained RL
+- Add custom constraints via wrapper or logic class
+
+- Violation logging and reward shaping
+
+- Safe vs unsafe episode tracking
+
+#### 🔍 Explainability
+- SaliencyExplainer — gradient-based visual heatmaps
+
+- SHAPExplainer — feature contribution values per decision
+
+- Compatible with any PyTorch-based agent
+
+#### 📊 Metrics
+- Constraint violation rate
+
+- Episode reward
+
+- Cumulative safe reward
+
+- Action entropy & temporal behavior stats
+
+#### 📚 Modularity
+- Swap out agents, constraints, evaluators, or explainers
+
+- Supports Gym environments
+
+- Configurable training pipeline
+
+## 📜 Citation
+Coming soon after arXiv/preprint release.

saferl_lite-0.1.2/README.md

@@ -0,0 +1,187 @@
+# 🔐 SafeRL-Lite
+
+A **lightweight, explainable, and modular** Python library for **Constrained Reinforcement Learning (Safe RL)** with real-time **SHAP & saliency-based explainability**, custom metrics, and Gym-compatible wrappers.
+
+By: 
+- Satyam Mishra, Vision Mentors Ltd., Hanoi, Vietnam
+- Shivam Mishra, Phung Thao Vi, Vietnam National University, Hanoi, Vietnam
+- Dr. Vishwanath Bijalwan, SR University, Warangal, India
+- Dr. Vijay Bhaskar Semwal, MANIT, Bhopal, India
+- University of West London, London, UK
+
+<p align="center">
+  <a href="https://github.com/satyamcser/saferl-lite/blob/main/LICENSE">
+    <img src="https://img.shields.io/github/license/satyamcser/saferl-lite?style=flat-square" alt="License">
+  </a>
+  <a href="https://github.com/satyamcser/saferl-lite/stargazers">
+    <img src="https://img.shields.io/github/stars/satyamcser/saferl-lite?style=flat-square" alt="Stars">
+  </a>
+  <a href="https://pypi.org/project/saferl-lite/">
+    <img src="https://img.shields.io/pypi/v/saferl-lite?style=flat-square" alt="PyPI version">
+  </a>
+  <a href="https://github.com/satyamcser/saferl-lite/actions/workflows/ci.yml">
+    <img src="https://img.shields.io/github/actions/workflow/status/satyamcser/saferl-lite/ci.yml?branch=main&style=flat-square" alt="Build Status">
+  </a>
+</p>
+
+
+---
+
+## 🌟 Overview
+
+**SafeRL-Lite** empowers reinforcement learning agents to act under **safety constraints**, while remaining **interpretable** and **modular** for fast experimentation. It wraps standard Gym environments and DQN-based agents with:
+
+- ✅ Safety constraint logic
+- 🔍 Visual explainability (SHAP, saliency maps)
+- 📊 Violation and reward tracking
+- 🧪 Built-in testing and evaluations
+
+---
+
+## ✅ Problem We Solved
+
+Modern Reinforcement Learning (RL) agents are powerful but unsafe and opaque:
+
+- 🚫 They frequently violate safety constraints during learning or deployment (e.g., fall off a cliff in navigation tasks).
+
+- 😕 Their decision-making is a black box: humans can’t understand why a certain action was chosen.
+
+- 🔍 Standard RL libraries lack native support for:
+
+  - Enforcing hard constraints during training.
+
+  - Explaining decisions using methods like SHAP or saliency maps.
+
+## ✅ Our Solution
+SafeRL-Lite is a lightweight Python library that:
+
+1. 📏 Adds a SafetyWrapper around any Gym environment to enforce safety constraints (e.g., bounding actions, limiting states).
+
+2. 🧠 Integrates explainability methods:
+
+  - SHAPExplainer (model-agnostic local explanations).
+
+  - SaliencyExplainer (gradient-based sensitivity maps).
+
+3. 🔧 Wraps Constrained DQNs with ease, enabling safety-compliant Q-learning.
+
+4. 📊 Offers built-in metrics like violation count and safe episode tracking.
+
+## ✅ Novelty
+While Safe RL and Explainable RL are separately studied, no prior lightweight library:
+
+- Combines hard safety constraints with post-hoc interpretability.
+
+- Is designed to be minimal, pluggable, and easily installable (pip install saferl-lite) for education, experimentation, or safe deployment.
+
+- Enables real-time SHAP or saliency visualization for Gym-based agents out-of-the-box.
+``` bash
+SafeRL-Lite is the first minimal library to unify constraint satisfaction and explainability in reinforcement learning — without heavy dependencies or overhead.
+```
+
+## ✅ Our Contribution
+1. 🔐 Constraint Wrapper API: Drop-in Gym wrapper for defining and enforcing logical constraints on observations, actions, and reward signals.
+
+2. 🧠 Explainability Modules: Plug-and-play SHAP and saliency explainer classes for deep Q-networks.
+
+3. 📦 PyPI-Ready Toolkit: Easily installed, documented, and CI/CD tested; built for research and reproducibility.
+
+4. 📈 Metrics for Constraint Violation: Tracks unsafe episodes, per-step violations, and integrates cleanly with WandB or TensorBoard.
+
+## ✅ Technical Explanation
+- We define a custom SafeEnvWrapper(gym.Env) that:
+
+  - Intercepts actions.
+
+  - Applies logical rules or thresholding.
+
+  - Optionally overrides rewards or terminations if constraints are violated.
+
+- A ConstrainedDQNAgent uses:
+
+  - Safety-wrapped Gym envs.
+
+  - Standard Q-learning with optional penalty_on_violation flag.
+
+- Post-training, the SHAPExplainer and SaliencyExplainer:
+
+  - Generate local attributions using input perturbations or gradient norms.
+
+  - Can visualize per-state or per-action explanations.
+
+
+
+## ✅ Satyam's Explanation
+```bash
+Imagine you're teaching a robot to walk — but there’s lava on the floor!
+You don’t just want it to learn fast, you want it to stay safe and explain why it stepped left, not right.
+```
+SafeRL-Lite is like a safety helmet and voicebox for robots:
+
+- The helmet makes sure they don’t do dangerous stuff.
+
+- The voicebox lets them say why they made that move.
+
+## 🔧 Installation
+
+> 📦 PyPI 
+```bash
+pip install saferl-lite
+```
+
+## 🛠️ From source:
+
+```bash
+git clone https://github.com/satyamcser/saferl-lite.git
+cd saferl-lite
+pip install -e .
+```
+
+## 🚀 Quickstart
+Train a constrained DQN agent with saliency-based explainability:
+
+```bash
+python train.py --env CartPole-v1 --constraint pole_angle --explain shap
+```
+
+🔹 This:
+
+- Adds a pole-angle constraint wrapper to the Gym env
+
+- Logs violations
+
+- Displays SHAP or saliency explanations for agent decisions
+
+## 🧠 Features
+#### ✅ Constrained RL
+- Add custom constraints via wrapper or logic class
+
+- Violation logging and reward shaping
+
+- Safe vs unsafe episode tracking
+
+#### 🔍 Explainability
+- SaliencyExplainer — gradient-based visual heatmaps
+
+- SHAPExplainer — feature contribution values per decision
+
+- Compatible with any PyTorch-based agent
+
+#### 📊 Metrics
+- Constraint violation rate
+
+- Episode reward
+
+- Cumulative safe reward
+
+- Action entropy & temporal behavior stats
+
+#### 📚 Modularity
+- Swap out agents, constraints, evaluators, or explainers
+
+- Supports Gym environments
+
+- Configurable training pipeline
+
+## 📜 Citation
+Coming soon after arXiv/preprint release.

{saferl_lite-0.1.0 → saferl_lite-0.1.2}/docs/about.md

@@ -59,7 +59,7 @@ This project is licensed under the **MIT License**. See the [LICENSE](https://gi
 ## 🌐 Links
 
 - GitHub: [https://github.com/satyamcser/saferl-lite](https://github.com/satyamcser/saferl-lite)
-- PyPI: *Coming soon*
+- PyPI: [https://pypi.org/project/saferl-lite/](https://pypi.org/project/saferl-lite/)
 - Docs: *This site*
 
 ---

saferl_lite-0.1.2/saferl_lite.egg-info/PKG-INFO

@@ -0,0 +1,239 @@
+Metadata-Version: 2.4
+Name: saferl-lite
+Version: 0.1.2
+Summary: A lightweight, explainable, and constrained reinforcement learning toolkit.
+Home-page: https://github.com/satyamcser/saferl-lite
+Author: Satyam Mishra
+Author-email: satyam@example.com
+Project-URL: Documentation, https://github.com/satyamcser/saferl-lite/tree/main/docs
+Project-URL: Source, https://github.com/satyamcser/saferl-lite
+Project-URL: Bug Tracker, https://github.com/satyamcser/saferl-lite/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: gym
+Requires-Dist: gymnasium
+Requires-Dist: numpy
+Requires-Dist: torch
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: pre-commit
+Requires-Dist: flake8
+Requires-Dist: pyyaml
+Requires-Dist: shap
+Requires-Dist: captum
+Requires-Dist: typer
+Requires-Dist: scikit-learn
+Requires-Dist: pandas
+Requires-Dist: pytest
+Requires-Dist: pytest-cov
+Requires-Dist: coverage
+Requires-Dist: mkdocs
+Requires-Dist: wandb
+Requires-Dist: mkdocs>=1.5
+Requires-Dist: mkdocs-material>=9.5
+Requires-Dist: mkdocstrings[python]
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# 🔐 SafeRL-Lite
+
+A **lightweight, explainable, and modular** Python library for **Constrained Reinforcement Learning (Safe RL)** with real-time **SHAP & saliency-based explainability**, custom metrics, and Gym-compatible wrappers.
+
+By: 
+- Satyam Mishra, Vision Mentors Ltd., Hanoi, Vietnam
+- Shivam Mishra, Phung Thao Vi, Vietnam National University, Hanoi, Vietnam
+- Dr. Vishwanath Bijalwan, SR University, Warangal, India
+- Dr. Vijay Bhaskar Semwal, MANIT, Bhopal, India
+- University of West London, London, UK
+
+<p align="center">
+  <a href="https://github.com/satyamcser/saferl-lite/blob/main/LICENSE">
+    <img src="https://img.shields.io/github/license/satyamcser/saferl-lite?style=flat-square" alt="License">
+  </a>
+  <a href="https://github.com/satyamcser/saferl-lite/stargazers">
+    <img src="https://img.shields.io/github/stars/satyamcser/saferl-lite?style=flat-square" alt="Stars">
+  </a>
+  <a href="https://pypi.org/project/saferl-lite/">
+    <img src="https://img.shields.io/pypi/v/saferl-lite?style=flat-square" alt="PyPI version">
+  </a>
+  <a href="https://github.com/satyamcser/saferl-lite/actions/workflows/ci.yml">
+    <img src="https://img.shields.io/github/actions/workflow/status/satyamcser/saferl-lite/ci.yml?branch=main&style=flat-square" alt="Build Status">
+  </a>
+</p>
+
+
+---
+
+## 🌟 Overview
+
+**SafeRL-Lite** empowers reinforcement learning agents to act under **safety constraints**, while remaining **interpretable** and **modular** for fast experimentation. It wraps standard Gym environments and DQN-based agents with:
+
+- ✅ Safety constraint logic
+- 🔍 Visual explainability (SHAP, saliency maps)
+- 📊 Violation and reward tracking
+- 🧪 Built-in testing and evaluations
+
+---
+
+## ✅ Problem We Solved
+
+Modern Reinforcement Learning (RL) agents are powerful but unsafe and opaque:
+
+- 🚫 They frequently violate safety constraints during learning or deployment (e.g., fall off a cliff in navigation tasks).
+
+- 😕 Their decision-making is a black box: humans can’t understand why a certain action was chosen.
+
+- 🔍 Standard RL libraries lack native support for:
+
+  - Enforcing hard constraints during training.
+
+  - Explaining decisions using methods like SHAP or saliency maps.
+
+## ✅ Our Solution
+SafeRL-Lite is a lightweight Python library that:
+
+1. 📏 Adds a SafetyWrapper around any Gym environment to enforce safety constraints (e.g., bounding actions, limiting states).
+
+2. 🧠 Integrates explainability methods:
+
+  - SHAPExplainer (model-agnostic local explanations).
+
+  - SaliencyExplainer (gradient-based sensitivity maps).
+
+3. 🔧 Wraps Constrained DQNs with ease, enabling safety-compliant Q-learning.
+
+4. 📊 Offers built-in metrics like violation count and safe episode tracking.
+
+## ✅ Novelty
+While Safe RL and Explainable RL are separately studied, no prior lightweight library:
+
+- Combines hard safety constraints with post-hoc interpretability.
+
+- Is designed to be minimal, pluggable, and easily installable (pip install saferl-lite) for education, experimentation, or safe deployment.
+
+- Enables real-time SHAP or saliency visualization for Gym-based agents out-of-the-box.
+``` bash
+SafeRL-Lite is the first minimal library to unify constraint satisfaction and explainability in reinforcement learning — without heavy dependencies or overhead.
+```
+
+## ✅ Our Contribution
+1. 🔐 Constraint Wrapper API: Drop-in Gym wrapper for defining and enforcing logical constraints on observations, actions, and reward signals.
+
+2. 🧠 Explainability Modules: Plug-and-play SHAP and saliency explainer classes for deep Q-networks.
+
+3. 📦 PyPI-Ready Toolkit: Easily installed, documented, and CI/CD tested; built for research and reproducibility.
+
+4. 📈 Metrics for Constraint Violation: Tracks unsafe episodes, per-step violations, and integrates cleanly with WandB or TensorBoard.
+
+## ✅ Technical Explanation
+- We define a custom SafeEnvWrapper(gym.Env) that:
+
+  - Intercepts actions.
+
+  - Applies logical rules or thresholding.
+
+  - Optionally overrides rewards or terminations if constraints are violated.
+
+- A ConstrainedDQNAgent uses:
+
+  - Safety-wrapped Gym envs.
+
+  - Standard Q-learning with optional penalty_on_violation flag.
+
+- Post-training, the SHAPExplainer and SaliencyExplainer:
+
+  - Generate local attributions using input perturbations or gradient norms.
+
+  - Can visualize per-state or per-action explanations.
+
+
+
+## ✅ Satyam's Explanation
+```bash
+Imagine you're teaching a robot to walk — but there’s lava on the floor!
+You don’t just want it to learn fast, you want it to stay safe and explain why it stepped left, not right.
+```
+SafeRL-Lite is like a safety helmet and voicebox for robots:
+
+- The helmet makes sure they don’t do dangerous stuff.
+
+- The voicebox lets them say why they made that move.
+
+## 🔧 Installation
+
+> 📦 PyPI 
+```bash
+pip install saferl-lite
+```
+
+## 🛠️ From source:
+
+```bash
+git clone https://github.com/satyamcser/saferl-lite.git
+cd saferl-lite
+pip install -e .
+```
+
+## 🚀 Quickstart
+Train a constrained DQN agent with saliency-based explainability:
+
+```bash
+python train.py --env CartPole-v1 --constraint pole_angle --explain shap
+```
+
+🔹 This:
+
+- Adds a pole-angle constraint wrapper to the Gym env
+
+- Logs violations
+
+- Displays SHAP or saliency explanations for agent decisions
+
+## 🧠 Features
+#### ✅ Constrained RL
+- Add custom constraints via wrapper or logic class
+
+- Violation logging and reward shaping
+
+- Safe vs unsafe episode tracking
+
+#### 🔍 Explainability
+- SaliencyExplainer — gradient-based visual heatmaps
+
+- SHAPExplainer — feature contribution values per decision
+
+- Compatible with any PyTorch-based agent
+
+#### 📊 Metrics
+- Constraint violation rate
+
+- Episode reward
+
+- Cumulative safe reward
+
+- Action entropy & temporal behavior stats
+
+#### 📚 Modularity
+- Swap out agents, constraints, evaluators, or explainers
+
+- Supports Gym environments
+
+- Configurable training pipeline
+
+## 📜 Citation
+Coming soon after arXiv/preprint release.

{saferl_lite-0.1.0 → saferl_lite-0.1.2}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name="saferl-lite",
-    version="0.1.0",
+    version="0.1.2",
     author="Satyam Mishra",
     author_email="satyam@example.com",
     description="A lightweight, explainable, and constrained reinforcement learning toolkit.",
@@ -10,7 +10,7 @@ setup(
     long_description_content_type="text/markdown",
     url="https://github.com/satyamcser/saferl-lite",
     project_urls={
-        "Documentation": "https://satyamcser.github.io/saferl-lite/",
+        "Documentation": "https://github.com/satyamcser/saferl-lite/tree/main/docs",
         "Source": "https://github.com/satyamcser/saferl-lite",
         "Bug Tracker": "https://github.com/satyamcser/saferl-lite/issues",
     },

saferl_lite-0.1.0/PKG-INFO

@@ -1,139 +0,0 @@
-Metadata-Version: 2.4
-Name: saferl-lite
-Version: 0.1.0
-Summary: A lightweight, explainable, and constrained reinforcement learning toolkit.
-Home-page: https://github.com/satyamcser/saferl-lite
-Author: Satyam Mishra
-Author-email: satyam@example.com
-Project-URL: Documentation, https://satyamcser.github.io/saferl-lite/
-Project-URL: Source, https://github.com/satyamcser/saferl-lite
-Project-URL: Bug Tracker, https://github.com/satyamcser/saferl-lite/issues
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Intended Audience :: Science/Research
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: gym
-Requires-Dist: gymnasium
-Requires-Dist: numpy
-Requires-Dist: torch
-Requires-Dist: matplotlib
-Requires-Dist: seaborn
-Requires-Dist: pre-commit
-Requires-Dist: flake8
-Requires-Dist: pyyaml
-Requires-Dist: shap
-Requires-Dist: captum
-Requires-Dist: typer
-Requires-Dist: scikit-learn
-Requires-Dist: pandas
-Requires-Dist: pytest
-Requires-Dist: pytest-cov
-Requires-Dist: coverage
-Requires-Dist: mkdocs
-Requires-Dist: wandb
-Requires-Dist: mkdocs>=1.5
-Requires-Dist: mkdocs-material>=9.5
-Requires-Dist: mkdocstrings[python]
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: license-file
-Dynamic: project-url
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
-# 🔐 SafeRL-Lite
-
-A **lightweight, explainable, and modular** Python library for **Constrained Reinforcement Learning (Safe RL)** with real-time **SHAP & saliency-based explainability**, custom metrics, and Gym-compatible wrappers.
-
-<p align="center">
-  <img src="https://img.shields.io/github/license/satyamcser/saferl-lite?style=flat-square">
-  <img src="https://img.shields.io/github/stars/satyamcser/saferl-lite?style=flat-square">
-  <img src="https://img.shields.io/pypi/v/saferl-lite?style=flat-square">
-  <img src="https://img.shields.io/github/actions/workflow/status/satyamcser/saferl-lite/ci.yml?branch=main&style=flat-square">
-</p>
-
----
-
-## 🌟 Overview
-
-**SafeRL-Lite** empowers reinforcement learning agents to act under **safety constraints**, while remaining **interpretable** and **modular** for fast experimentation. It wraps standard Gym environments and DQN-based agents with:
-
-- ✅ Safety constraint logic
-- 🔍 Visual explainability (SHAP, saliency maps)
-- 📊 Violation and reward tracking
-- 🧪 Built-in testing and evaluations
-
----
-
-## 🔧 Installation
-
-> 📦 PyPI (coming soon)
-```bash
-pip install saferl-lite
-```
-
-## 🛠️ From source:
-
-```bash
-git clone https://github.com/satyamcser/saferl-lite.git
-cd saferl-lite
-pip install -e .
-```
-
-## 🚀 Quickstart
-Train a constrained DQN agent with saliency-based explainability:
-
-```bash
-python train.py --env CartPole-v1 --constraint pole_angle --explain shap
-```
-
-🔹 This:
-
-- Adds a pole-angle constraint wrapper to the Gym env
-
-- Logs violations
-
-- Displays SHAP or saliency explanations for agent decisions
-
-## 🧠 Features
-#### ✅ Constrained RL
-- Add custom constraints via wrapper or logic class
-
-- Violation logging and reward shaping
-
-- Safe vs unsafe episode tracking
-
-#### 🔍 Explainability
-- SaliencyExplainer — gradient-based visual heatmaps
-
-- SHAPExplainer — feature contribution values per decision
-
-- Compatible with any PyTorch-based agent
-
-#### 📊 Metrics
-- Constraint violation rate
-
-- Episode reward
-
-- Cumulative safe reward
-
-- Action entropy & temporal behavior stats
-
-#### 📚 Modularity
-- Swap out agents, constraints, evaluators, or explainers
-
-- Supports Gym environments
-
-- Configurable training pipeline
-
-## 📜 Citation
-Coming soon after arXiv/preprint release.

saferl_lite-0.1.0/README.md

@@ -1,87 +0,0 @@
-# 🔐 SafeRL-Lite
-
-A **lightweight, explainable, and modular** Python library for **Constrained Reinforcement Learning (Safe RL)** with real-time **SHAP & saliency-based explainability**, custom metrics, and Gym-compatible wrappers.
-
-<p align="center">
-  <img src="https://img.shields.io/github/license/satyamcser/saferl-lite?style=flat-square">
-  <img src="https://img.shields.io/github/stars/satyamcser/saferl-lite?style=flat-square">
-  <img src="https://img.shields.io/pypi/v/saferl-lite?style=flat-square">
-  <img src="https://img.shields.io/github/actions/workflow/status/satyamcser/saferl-lite/ci.yml?branch=main&style=flat-square">
-</p>
-
----
-
-## 🌟 Overview
-
-**SafeRL-Lite** empowers reinforcement learning agents to act under **safety constraints**, while remaining **interpretable** and **modular** for fast experimentation. It wraps standard Gym environments and DQN-based agents with:
-
-- ✅ Safety constraint logic
-- 🔍 Visual explainability (SHAP, saliency maps)
-- 📊 Violation and reward tracking
-- 🧪 Built-in testing and evaluations
-
----
-
-## 🔧 Installation
-
-> 📦 PyPI (coming soon)
-```bash
-pip install saferl-lite
-```
-
-## 🛠️ From source:
-
-```bash
-git clone https://github.com/satyamcser/saferl-lite.git
-cd saferl-lite
-pip install -e .
-```
-
-## 🚀 Quickstart
-Train a constrained DQN agent with saliency-based explainability:
-
-```bash
-python train.py --env CartPole-v1 --constraint pole_angle --explain shap
-```
-
-🔹 This:
-
-- Adds a pole-angle constraint wrapper to the Gym env
-
-- Logs violations
-
-- Displays SHAP or saliency explanations for agent decisions
-
-## 🧠 Features
-#### ✅ Constrained RL
-- Add custom constraints via wrapper or logic class
-
-- Violation logging and reward shaping
-
-- Safe vs unsafe episode tracking
-
-#### 🔍 Explainability
-- SaliencyExplainer — gradient-based visual heatmaps
-
-- SHAPExplainer — feature contribution values per decision
-
-- Compatible with any PyTorch-based agent
-
-#### 📊 Metrics
-- Constraint violation rate
-
-- Episode reward
-
-- Cumulative safe reward
-
-- Action entropy & temporal behavior stats
-
-#### 📚 Modularity
-- Swap out agents, constraints, evaluators, or explainers
-
-- Supports Gym environments
-
-- Configurable training pipeline
-
-## 📜 Citation
-Coming soon after arXiv/preprint release.

saferl_lite-0.1.0/saferl_lite.egg-info/PKG-INFO

@@ -1,139 +0,0 @@
-Metadata-Version: 2.4
-Name: saferl-lite
-Version: 0.1.0
-Summary: A lightweight, explainable, and constrained reinforcement learning toolkit.
-Home-page: https://github.com/satyamcser/saferl-lite
-Author: Satyam Mishra
-Author-email: satyam@example.com
-Project-URL: Documentation, https://satyamcser.github.io/saferl-lite/
-Project-URL: Source, https://github.com/satyamcser/saferl-lite
-Project-URL: Bug Tracker, https://github.com/satyamcser/saferl-lite/issues
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Intended Audience :: Science/Research
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: gym
-Requires-Dist: gymnasium
-Requires-Dist: numpy
-Requires-Dist: torch
-Requires-Dist: matplotlib
-Requires-Dist: seaborn
-Requires-Dist: pre-commit
-Requires-Dist: flake8
-Requires-Dist: pyyaml
-Requires-Dist: shap
-Requires-Dist: captum
-Requires-Dist: typer
-Requires-Dist: scikit-learn
-Requires-Dist: pandas
-Requires-Dist: pytest
-Requires-Dist: pytest-cov
-Requires-Dist: coverage
-Requires-Dist: mkdocs
-Requires-Dist: wandb
-Requires-Dist: mkdocs>=1.5
-Requires-Dist: mkdocs-material>=9.5
-Requires-Dist: mkdocstrings[python]
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: license-file
-Dynamic: project-url
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
-# 🔐 SafeRL-Lite
-
-A **lightweight, explainable, and modular** Python library for **Constrained Reinforcement Learning (Safe RL)** with real-time **SHAP & saliency-based explainability**, custom metrics, and Gym-compatible wrappers.
-
-<p align="center">
-  <img src="https://img.shields.io/github/license/satyamcser/saferl-lite?style=flat-square">
-  <img src="https://img.shields.io/github/stars/satyamcser/saferl-lite?style=flat-square">
-  <img src="https://img.shields.io/pypi/v/saferl-lite?style=flat-square">
-  <img src="https://img.shields.io/github/actions/workflow/status/satyamcser/saferl-lite/ci.yml?branch=main&style=flat-square">
-</p>
-
----
-
-## 🌟 Overview
-
-**SafeRL-Lite** empowers reinforcement learning agents to act under **safety constraints**, while remaining **interpretable** and **modular** for fast experimentation. It wraps standard Gym environments and DQN-based agents with:
-
-- ✅ Safety constraint logic
-- 🔍 Visual explainability (SHAP, saliency maps)
-- 📊 Violation and reward tracking
-- 🧪 Built-in testing and evaluations
-
----
-
-## 🔧 Installation
-
-> 📦 PyPI (coming soon)
-```bash
-pip install saferl-lite
-```
-
-## 🛠️ From source:
-
-```bash
-git clone https://github.com/satyamcser/saferl-lite.git
-cd saferl-lite
-pip install -e .
-```
-
-## 🚀 Quickstart
-Train a constrained DQN agent with saliency-based explainability:
-
-```bash
-python train.py --env CartPole-v1 --constraint pole_angle --explain shap
-```
-
-🔹 This:
-
-- Adds a pole-angle constraint wrapper to the Gym env
-
-- Logs violations
-
-- Displays SHAP or saliency explanations for agent decisions
-
-## 🧠 Features
-#### ✅ Constrained RL
-- Add custom constraints via wrapper or logic class
-
-- Violation logging and reward shaping
-
-- Safe vs unsafe episode tracking
-
-#### 🔍 Explainability
-- SaliencyExplainer — gradient-based visual heatmaps
-
-- SHAPExplainer — feature contribution values per decision
-
-- Compatible with any PyTorch-based agent
-
-#### 📊 Metrics
-- Constraint violation rate
-
-- Episode reward
-
-- Cumulative safe reward
-
-- Action entropy & temporal behavior stats
-
-#### 📚 Modularity
-- Swap out agents, constraints, evaluators, or explainers
-
-- Supports Gym environments
-
-- Configurable training pipeline
-
-## 📜 Citation
-Coming soon after arXiv/preprint release.