evolib 0.2.0b4.dev9__tar.gz → 0.3.0__tar.gz

{evolib-0.2.0b4.dev9/evolib.egg-info → evolib-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: evolib
-Version: 0.2.0b4.dev9
+Version: 0.3.0
 Summary: A modular framework for evolutionary strategies and neuroevolution.
 Author-email: EvoLib <evolib@dismail.de>
 License: MIT License
@@ -25,7 +25,7 @@ License: MIT License
         OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
         SOFTWARE.
         
-Classifier: Development Status :: 4 - Beta
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.12
@@ -41,20 +41,29 @@ Requires-Dist: pydantic<3.0,>=2.7
 Requires-Dist: graphviz>=0.20.1
 Requires-Dist: evonet<0.2,>=0.1.0.dev5
 Requires-Dist: matplotlib>=3.10
+Requires-Dist: gymnasium[box2d]
+Requires-Dist: imageio
+Requires-Dist: pygame>=2.5
+Requires-Dist: pillow>=10.0
 Provides-Extra: dev
-Requires-Dist: mypy; extra == "dev"
+Requires-Dist: black==25.1.0; extra == "dev"
+Requires-Dist: isort==6.0.1; extra == "dev"
+Requires-Dist: flake8==7.3.0; extra == "dev"
+Requires-Dist: mypy==1.16.1; extra == "dev"
+Requires-Dist: pytest==8.4.1; extra == "dev"
+Requires-Dist: pytest-cov==5.0.0; extra == "dev"
+Requires-Dist: docformatter==1.7.5; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"
-Requires-Dist: ray; extra == "dev"
-Requires-Dist: gymnasium; extra == "dev"
-Requires-Dist: imageio; extra == "dev"
-Requires-Dist: Box2D; extra == "dev"
+Requires-Dist: matplotlib; extra == "dev"
 Provides-Extra: docs
 Requires-Dist: sphinx; extra == "docs"
 Requires-Dist: sphinx-rtd-theme; extra == "docs"
 Requires-Dist: myst-parser; extra == "docs"
 Provides-Extra: test
-Requires-Dist: pytest>=8; extra == "test"
-Requires-Dist: pytest-cov>=5; extra == "test"
+Requires-Dist: pytest==8.4.1; extra == "test"
+Requires-Dist: pytest-cov==5.0.0; extra == "test"
+Provides-Extra: parallel
+Requires-Dist: ray; extra == "parallel"
 Dynamic: license-file
 
 # EvoLib – A Modular Framework for Evolutionary Computation
@@ -63,7 +72,7 @@ Dynamic: license-file
 [![Code Quality & Tests](https://github.com/EvoLib/evo-lib/actions/workflows/ci.yml/badge.svg)](https://github.com/EvoLib/evo-lib/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 [![PyPI version](https://badge.fury.io/py/evolib.svg)](https://pypi.org/project/evolib/)
-[![Project Status: Beta](https://img.shields.io/badge/status-beta-blue.svg)](https://github.com/EvoLib/evo-lib)
+[![Project Status: Stable](https://img.shields.io/badge/status-stable-green.svg)](https://github.com/EvoLib/evo-lib)
 
 <p align="center">
   <img src="https://raw.githubusercontent.com/EvoLib/evolib/main/assets/evolib_256.png" alt="EvoLib Logo" width="256"/>
@@ -80,15 +89,14 @@ EvoLib is a lightweight and transparent framework for evolutionary computation,
 - **Educational value**: examples and a clean API make it practical for illustrating evolutionary concepts.  
 - **Neuroevolution support**: evolvable neural networks with explicit topology, recurrence, delays, and structural mutation (EvoNet).  
 - **Gymnasium integration**: run [Gymnasium](https://gymnasium.farama.org) benchmarks (e.g. CartPole, LunarLander) via a simple wrapper.
+- **EvoEnv**: build small, controllable Pygame environments for evolutionary experiments.
 - **Parallel evaluation (optional)**: basic support for [Ray](https://www.ray.io/) to speed up fitness evaluations.  
 - **HELI (Hierarchical Evolution with Lineage Incubation)**  
   Runs short micro-evolutions ("incubations") for structure-mutated individuals, allowing new topologies to stabilize before rejoining the main population.  
 - **Type-checked**: static typing with mypy, PEP8-compliant and consistent code style.  
 
-
-> **EvoLib is currently in beta. The core API and configuration format are stable, but some features are still under development.**
-
 ---
+
 <p align="center">
   <img src="https://raw.githubusercontent.com/EvoLib/evo-lib/main/examples/05_advanced_topics/04_frames_vector_obstacles/04_vector_control_obstacles.gif" alt="Sample Plot" width="512"/>
 </p>
@@ -97,11 +105,18 @@ EvoLib is a lightweight and transparent framework for evolutionary computation,
 
 ## Installation
 
+EvoLib requires Python 3.12 or newer.
+
 ```bash
 pip install evolib
 ```
 
-Requirements: Python 3.12+ and packages in `requirements.txt`.
+Install optional Ray-based parallel evaluation with:
+
+```bash
+pip install "evolib[parallel]"
+```
+
 
 ---
 
@@ -153,17 +168,33 @@ modules:
   controller:
     type: vector
     dim: 8
-    initializer: normal_vector
+    initializer: normal
     bounds: [-1.0, 1.0]
     mutation:
       strategy: adaptive_individual
       probability: 1.0
-      strength: 0.1
+      min_strength: 0.01
+      max_strength: 0.1
 
   brain:
     type: evonet
     dim: [4, 6, 2]
     activation: [linear, tanh, tanh]
+
+    connectivity:
+      recurrent: none
+      scope: adjacent
+      density: 1.0
+
+    weights:
+      initializer: uniform
+      bounds: [-1.0, 1.0]
+
+    bias:
+      initializer: normal
+      std: 0.1
+      bounds: [-0.5, 0.5]
+
     mutation:
       strategy: constant
       probability: 1.0
@@ -197,7 +228,7 @@ Documentation for EvoLib is available at: 👉 https://evolib.readthedocs.io/en/
 
 EvoLib is archived for long-term reproducibility on Zenodo.
 
-**DOI:** https://doi.org/10.5281/zenodo.17793862
+**DOI:** https://doi.org/10.5281/zenodo.18775372
 
 ---
 
@@ -238,27 +269,17 @@ gif = env.visualize(indiv, gen=10)    # render & save as GIF
 
 ---
 
-## Preview: Pygame Integration
+## EvoEnv
 
-Early prototypes demonstrate how evolutionary algorithms can evolve both neural networks and sensor properties such as number, range, and orientation for agents in 2D worlds built with pygame. This illustrates how networks and sensors co-adapt to dynamic environments with collisions and feedback.
-
-### Ant/Food Prototype
-In this video, agents use simple sensors to learn how to collect food while avoiding collisions with the environment.
+EvoEnv provides small, controllable Pygame environments for
+evolutionary experiments with EvoLib. Environments separate headless simulation,
+controller integration, and visualization.
 
 <p align="center">
-  <img src="https://raw.githubusercontent.com/EvoLib/evo-lib/main/assets/ant.gif" alt="Pygame Integration Preview" width="640"/>
+<img src="https://raw.githubusercontent.com/EvoLib/evo-lib/main/examples/09_evoenv/04_collector/collector.gif" alt="EvoEnv Collector example" width="512"/>
 </p>
 
-### Flappy Bird–style Prototype
-Another prototype uses a **Flappy Bird–like 2D world**, where agents must pass through moving gaps.
-Both the **neural controller** and the **sensors** (number, length, angle) are evolved, allowing perception and action to adapt together.
-This illustrates how EvoLib can be applied to simple game-like environments, making the joint evolution of sensing and control directly observable.
-
-<p align="center">
-  <img src="https://raw.githubusercontent.com/EvoLib/evo-lib/main/assets/flappy.gif" alt="Pygame Integration Preview" width="160"/>
-</p>
-
-*This video shows the best agent from the final generation rather than the full evolutionary process.*
+👉 [Examples](https://github.com/EvoLib/evo-lib/tree/main/examples/09_evoenv/README.md)
 
 ---
 
@@ -270,7 +291,7 @@ EvoLib includes a small set of examples that illustrate the core concepts step b
 2. [Strategies in Action](examples/02_strategies/03_mu_lambda.py) – (μ + λ) evolution step by step.
 3. [Function Approximation](examples/04_function_approximation/02_sine_point_approximation.py) – evolve support points to match a sine curve.
 4. [Evolution as Control](examples/05_advanced_topics/04_vector_control_with_obstacles.py) – evolve a controller in an environment.
-5. [Neuroevolution with Structural Growth](examples/07_evonet/03_structural_xor.py) – evolve networks with growing topology.
+5. [Neuroevolution with Structural Growth](examples/07_evonet/06_structural_xor.py) – evolve networks with growing topology.
 
 For deeper exploration, see the [full examples directory](examples/)
 
@@ -284,11 +305,9 @@ For deeper exploration, see the [full examples directory](examples/)
 - [X] Composite Parameters (multi-module individuals)
 - [X] Neuroevolution
 - [X] Topological Evolution (neurons, edges)
-- [X] Ray Support for Parallel Evaluation (early prototypes)
-- [X] OpenAI Gymnasium / Gym Wrapper
-- [ ] Advanced Visualization
-- [ ] Game Environment Integration (pygame, PettingZoo - early prototypes)
-
+- [X] Ray Support for Parallel Evaluation
+- [X] Gymnasium Integration
+- [X] EvoEnv for small Pygame-based evolutionary environments
 
 ---
 

{evolib-0.2.0b4.dev9 → evolib-0.3.0}/README.md

@@ -4,7 +4,7 @@
 [![Code Quality & Tests](https://github.com/EvoLib/evo-lib/actions/workflows/ci.yml/badge.svg)](https://github.com/EvoLib/evo-lib/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 [![PyPI version](https://badge.fury.io/py/evolib.svg)](https://pypi.org/project/evolib/)
-[![Project Status: Beta](https://img.shields.io/badge/status-beta-blue.svg)](https://github.com/EvoLib/evo-lib)
+[![Project Status: Stable](https://img.shields.io/badge/status-stable-green.svg)](https://github.com/EvoLib/evo-lib)
 
 <p align="center">
   <img src="https://raw.githubusercontent.com/EvoLib/evolib/main/assets/evolib_256.png" alt="EvoLib Logo" width="256"/>
@@ -21,15 +21,14 @@ EvoLib is a lightweight and transparent framework for evolutionary computation,
 - **Educational value**: examples and a clean API make it practical for illustrating evolutionary concepts.  
 - **Neuroevolution support**: evolvable neural networks with explicit topology, recurrence, delays, and structural mutation (EvoNet).  
 - **Gymnasium integration**: run [Gymnasium](https://gymnasium.farama.org) benchmarks (e.g. CartPole, LunarLander) via a simple wrapper.
+- **EvoEnv**: build small, controllable Pygame environments for evolutionary experiments.
 - **Parallel evaluation (optional)**: basic support for [Ray](https://www.ray.io/) to speed up fitness evaluations.  
 - **HELI (Hierarchical Evolution with Lineage Incubation)**  
   Runs short micro-evolutions ("incubations") for structure-mutated individuals, allowing new topologies to stabilize before rejoining the main population.  
 - **Type-checked**: static typing with mypy, PEP8-compliant and consistent code style.  
 
-
-> **EvoLib is currently in beta. The core API and configuration format are stable, but some features are still under development.**
-
 ---
+
 <p align="center">
   <img src="https://raw.githubusercontent.com/EvoLib/evo-lib/main/examples/05_advanced_topics/04_frames_vector_obstacles/04_vector_control_obstacles.gif" alt="Sample Plot" width="512"/>
 </p>
@@ -38,11 +37,18 @@ EvoLib is a lightweight and transparent framework for evolutionary computation,
 
 ## Installation
 
+EvoLib requires Python 3.12 or newer.
+
 ```bash
 pip install evolib
 ```
 
-Requirements: Python 3.12+ and packages in `requirements.txt`.
+Install optional Ray-based parallel evaluation with:
+
+```bash
+pip install "evolib[parallel]"
+```
+
 
 ---
 
@@ -94,17 +100,33 @@ modules:
   controller:
     type: vector
     dim: 8
-    initializer: normal_vector
+    initializer: normal
     bounds: [-1.0, 1.0]
     mutation:
       strategy: adaptive_individual
       probability: 1.0
-      strength: 0.1
+      min_strength: 0.01
+      max_strength: 0.1
 
   brain:
     type: evonet
     dim: [4, 6, 2]
     activation: [linear, tanh, tanh]
+
+    connectivity:
+      recurrent: none
+      scope: adjacent
+      density: 1.0
+
+    weights:
+      initializer: uniform
+      bounds: [-1.0, 1.0]
+
+    bias:
+      initializer: normal
+      std: 0.1
+      bounds: [-0.5, 0.5]
+
     mutation:
       strategy: constant
       probability: 1.0
@@ -138,7 +160,7 @@ Documentation for EvoLib is available at: 👉 https://evolib.readthedocs.io/en/
 
 EvoLib is archived for long-term reproducibility on Zenodo.
 
-**DOI:** https://doi.org/10.5281/zenodo.17793862
+**DOI:** https://doi.org/10.5281/zenodo.18775372
 
 ---
 
@@ -179,27 +201,17 @@ gif = env.visualize(indiv, gen=10)    # render & save as GIF
 
 ---
 
-## Preview: Pygame Integration
+## EvoEnv
 
-Early prototypes demonstrate how evolutionary algorithms can evolve both neural networks and sensor properties such as number, range, and orientation for agents in 2D worlds built with pygame. This illustrates how networks and sensors co-adapt to dynamic environments with collisions and feedback.
-
-### Ant/Food Prototype
-In this video, agents use simple sensors to learn how to collect food while avoiding collisions with the environment.
+EvoEnv provides small, controllable Pygame environments for
+evolutionary experiments with EvoLib. Environments separate headless simulation,
+controller integration, and visualization.
 
 <p align="center">
-  <img src="https://raw.githubusercontent.com/EvoLib/evo-lib/main/assets/ant.gif" alt="Pygame Integration Preview" width="640"/>
+<img src="https://raw.githubusercontent.com/EvoLib/evo-lib/main/examples/09_evoenv/04_collector/collector.gif" alt="EvoEnv Collector example" width="512"/>
 </p>
 
-### Flappy Bird–style Prototype
-Another prototype uses a **Flappy Bird–like 2D world**, where agents must pass through moving gaps.
-Both the **neural controller** and the **sensors** (number, length, angle) are evolved, allowing perception and action to adapt together.
-This illustrates how EvoLib can be applied to simple game-like environments, making the joint evolution of sensing and control directly observable.
-
-<p align="center">
-  <img src="https://raw.githubusercontent.com/EvoLib/evo-lib/main/assets/flappy.gif" alt="Pygame Integration Preview" width="160"/>
-</p>
-
-*This video shows the best agent from the final generation rather than the full evolutionary process.*
+👉 [Examples](https://github.com/EvoLib/evo-lib/tree/main/examples/09_evoenv/README.md)
 
 ---
 
@@ -211,7 +223,7 @@ EvoLib includes a small set of examples that illustrate the core concepts step b
 2. [Strategies in Action](examples/02_strategies/03_mu_lambda.py) – (μ + λ) evolution step by step.
 3. [Function Approximation](examples/04_function_approximation/02_sine_point_approximation.py) – evolve support points to match a sine curve.
 4. [Evolution as Control](examples/05_advanced_topics/04_vector_control_with_obstacles.py) – evolve a controller in an environment.
-5. [Neuroevolution with Structural Growth](examples/07_evonet/03_structural_xor.py) – evolve networks with growing topology.
+5. [Neuroevolution with Structural Growth](examples/07_evonet/06_structural_xor.py) – evolve networks with growing topology.
 
 For deeper exploration, see the [full examples directory](examples/)
 
@@ -225,11 +237,9 @@ For deeper exploration, see the [full examples directory](examples/)
 - [X] Composite Parameters (multi-module individuals)
 - [X] Neuroevolution
 - [X] Topological Evolution (neurons, edges)
-- [X] Ray Support for Parallel Evaluation (early prototypes)
-- [X] OpenAI Gymnasium / Gym Wrapper
-- [ ] Advanced Visualization
-- [ ] Game Environment Integration (pygame, PettingZoo - early prototypes)
-
+- [X] Ray Support for Parallel Evaluation
+- [X] Gymnasium Integration
+- [X] EvoEnv for small Pygame-based evolutionary environments
 
 ---
 

{evolib-0.2.0b4.dev9 → evolib-0.3.0}/docs/config_guide.md

@@ -100,7 +100,7 @@ modules:
   ys:
     type: vector
     dim: 6
-    initializer: zero_vector
+    initializer: zero
     bounds: [-1.5, 1.5]
     mutation:
       strategy: constant
@@ -120,6 +120,11 @@ This configuration demonstrates EvoNet evolution: weight mutation, bias-specific
 
 `dim: [2, 0, 0, 1]` starts with empty hidden layers, letting structural mutation grow nodes and edges.
 
+Connectivity:
+- `scope` controls which feedforward edges are allowed at initialization.
+- `density` controls how many of those allowed edges are actually created at init.
+- `recurrent` enables recurrent edge kinds (empty list means none).
+
 Topology constraints:
 - `max_neurons` and `max_connections` keep growth bounded (these are the current names; avoid older `max_nodes/max_edges`).
 
@@ -127,6 +132,8 @@ Delay:
 - `delay:` initializes delays of recurrent connections at build time.
 - `mutation.delay:` mutates delays during evolution (recurrent connections only).
 
+
+
 ```yaml
 parent_pool_size: 20
 offspring_pool_size: 40
@@ -145,17 +152,22 @@ modules:
     type: evonet
     dim: [2, 0, 0, 1]       # hidden layers start empty
     activation: [linear, tanh, tanh, sigmoid]
+
+    connectivity:
+      scope: crosslayer          # adjacent | crosslayer
+      density: 1.0               # (0, 1]
+      recurrent: [direct]        # [], [direct], [lateral], [indirect]
+    
     weights:
       initializer: normal
       std: 0.5
       bounds: [-5.0, 5.0]
+    
     bias:      
       initializer: normal
       std: 0.5
       bounds: [-1.0, 1.0]
 
-    recurrent: direct   # REQUIRED for delay to have any effect
-
     # NOTE: Delays only apply to recurrent connections.
     # If `recurrent` is not enabled, this block has no effect.
     delay:
@@ -220,6 +232,13 @@ modules:
 
 For expensive problems, EvoLib can evaluate individuals in parallel using Ray.
 
+Install the optional parallel evaluation support before selecting the Ray
+backend:
+
+```bash
+pip install "evolib[parallel]"
+```
+
 ```yaml
 parallel:
   backend: ray         # backend: none | ray

{evolib-0.2.0b4.dev9 → evolib-0.3.0}/docs/config_parameter.md

@@ -156,7 +156,7 @@ The `vector` module defines an evolvable parameter vector.
 | `bounds`                         | `tuple[float, float]`                             | `[-1.0, 1.0]`  | Hard clamp range applied after mutation. |
 | `init_bounds`                    | `tuple[float, float] \| null`                     | `null`         | Clamp applied only during initialization. Falls back to `bounds` if not set. |
 | `shape`                          | `tuple[int, ...] \| null`                         | `null`         | Optional explicit shape. If set, `dim = product(shape)`. Shape is retained as metadata. |
-| `values`                         | `list[float] \| null`                             | `null`         | Required for `initializer: fixed_vector`. If `dim` is omitted, it is inferred from `len(values)`. |
+| `values`                         | `list[float] \| null`                             | `null`         | Required for `initializer: fixed`. If `dim` is omitted, it is inferred from `len(values)`. |
 | `activation`                     | `str \| null`                                     | `null`         | Only relevant if `structure: "net"`. |
 | `mean`                           | `float \| null`                                   | `0.0`          | Mean parameter for normal-based initializers (if used by initializer). |
 | `std`                            | `float \| null`                                   | `1.0`          | Standard deviation for normal-based initializers (if used by initializer). |
@@ -246,7 +246,7 @@ modules:
 modules:
   main:
     type: vector
-    initializer: fixed_vector
+    initializer: fixed
     values: [0.0, 1.0, 0.5, -0.5]
     bounds: [-1.0, 1.0]
 
@@ -264,7 +264,7 @@ modules:
     type: vector
     structure: flat
     dim: 6
-    initializer: normal_vector
+    initializer: normal
     mean: 0.0
     std: 0.2
     bounds: [-1.0, 1.0]
@@ -289,12 +289,30 @@ modules:
 | `dim`             | list[int]           | —       | Layer sizes, e.g. `[4, 0, 0, 2]`. Hidden layers can start empty (0) and grow through structural mutation. |
 | `activation`      | str \| list[str]    | —       | If list: activation per layer. If str: used for non-input layers; input layer is treated as linear. |
 | `initializer`     | str                 | default | Topology preset (e.g. `default`, `unconnected`, `identity`). Parameter initialization is configured via `weights`, `bias`, and `delay`. |
+| `connectivity`    | `dict`                   | —       | **Required.** Defines feedforward scope/density and allowed recurrent kinds. |
 | `weights`         | dict                | —       | Weight init and bounds configuration (initializer, bounds, optional params). | 
 | `bias`            | dict                | —       | Bias init and bounds configuration (initializer, bounds, optional params). | 
 | `neuron_dynamics` | list[dict] \| null  | null    | Optional per-layer neuron dynamics specification. Must match `len(dim)`. |
 | `mutation`        | dict \| null        | null    | Mutation settings for weights, biases, activations, delay, and structure. |
 | `crossover`       | dict \| null        | null    | Optional crossover settings (weight/bias level). |
 
+#### Connectivity (`connectivity`)
+
+| Field       | Type                         | Default | Notes |
+|------------|------------------------------|---------|------|
+| `scope`    | `"adjacent" \| "crosslayer"` | —       | **Required.** Allowed feedforward edge scope at initialization. |
+| `density`  | `float`                      | —       | **Required.** Fraction of allowed feedforward edges created at init `(0,1]`. |
+| `recurrent`| `list[str]`                  | `[]`    | Allowed recurrent edge kinds. Empty list means none. |
+
+Example:
+
+```yaml
+connectivity:
+  scope: crosslayer
+  density: 0.5
+  recurrent: [direct]
+```
+
 ##### weights block
 |Parameter	 | Type	 | Default	 | Explanation |
 |------------|-------|-----------|-------------|
@@ -325,8 +343,8 @@ Allowed presets:
 | Initializer            | Meaning (topology only) |
 |------------------------|-------------------------|
 | `default`       | Standard EvoNet topology preset (uses `connection_scope`, `connection_density`, and `recurrent`). |
-| `unconnected_evonet`   | Creates neurons/layers but starts with **no connections** (use structural mutation to grow). |
-| `identity_evonet`      | Special preset intended for stable recurrent memory (may override parameters internally; see notes below). |
+| `unconnected`   | Creates neurons/layers but starts with **no connections** (use structural mutation to grow). |
+| `identity`      | Special preset intended for stable recurrent memory (may override parameters internally; see notes below). |
 
 ---
 
@@ -493,13 +511,12 @@ structural:
 
 ### Topology constraints
 
-| Field                | Type          | Default  | Description |
-|---------------------|---------------|----------|-------------|
-| `recurrent`          | str           | `none`   | Controls recurrence: `none`, `direct`, `local` or `all`. |
-| `connection_scope`   | str           | `adjacent` | Allowed layer connectivity: `adjacent` (neighbor layers only) or `crosslayer` (any-to-any). |
-| `connection_density` | float         | 1.0     | Fraction of possible connections initialized at creation time. |
-| `max_neurons`        | int \| null   | null     | Maximum number of non-input neurons (`null` = unlimited). |
-| `max_connections`    | int \| null   | null     | Maximum number of edges (`null` = unlimited). |
+| Field              | Type                           | Default     | Description |
+|-------------------|--------------------------------|-------------|-------------|
+| `recurrent`        | `list[str]`                    | `[]`        | Allowed recurrent kinds for `add_connection`. Empty list means none. |
+| `connection_scope` | `"adjacent" \| "crosslayer" \| null` | `"adjacent"` | Constraint for structural add-neuron / add-connection edge placement. |
+| `max_neurons`      | `int \| null`                  | `null`      | Upper bound on total neurons allowed (implementation-defined counting). |
+| `max_connections`  | `int \| null`                  | `null`      | Upper bound on total connections allowed. |
 
 ---
 
@@ -531,7 +548,7 @@ modules:
   controller:
     type: vector
     dim: 8
-    initializer: normal_vector
+    initializer: normal
     bounds: [-1.0, 1.0]
     mutation:
       strategy: adaptive_individual
@@ -544,7 +561,10 @@ modules:
     type: evonet
     dim: [4, 0, 0, 2]
     activation: [linear, tanh, tanh, tanh]
-    initializer: normal_evonet
+
+    connectivity:
+      scope: adjacent
+      density: 1.0
 
     delay:
       initializer: uniform

evolib-0.3.0/docs/evoenv.md

@@ -0,0 +1,2 @@
+```{include} ../evoenv/README.md
+```

{evolib-0.2.0b4.dev9 → evolib-0.3.0}/docs/getting_started.md

@@ -40,7 +40,7 @@ modules:
   main:
     type: vector
     dim: 5
-    initializer: normal_vector
+    initializer: normal
     bounds: [-5.0, 5.0]
     mutation:
       strategy: constant

evolib-0.3.0/docs/index.md

@@ -0,0 +1,97 @@
+# EvoLib
+
+EvoLib is a framework for evolutionary computation, neuroevolution, and small
+controlled experiments.
+
+It uses explicit configuration and modular components. Evolutionary strategies,
+parameter representations, operators, and evaluation environments can be
+selected and combined separately.
+
+## Project areas
+
+* **Evolutionary strategies** — configurable selection, reproduction,
+  replacement, crossover, and mutation.
+* **Parameter representations** — vectors, network vectors, and EvoNet neural
+  networks.
+* **Neuroevolution** — evolution of weights, biases, activation functions,
+  recurrent connections, delays, and network structures.
+* **HELI** — lineage incubation for newly mutated network structures.
+* **Gymnasium integration** — evaluation and visualization using Gymnasium
+  environments.
+* **EvoEnv** — small Pygame-based environments for controlled evolutionary
+  experiments and teaching examples.
+* **Parallel evaluation** — optional Ray-based fitness evaluation.
+
+## Start here
+
+New users should begin with the
+[getting started guide](getting_started.md), followed by the
+[configuration guide](config_guide.md).
+
+The [configuration parameter reference](config_parameter.md) lists the
+available YAML settings. Documentation for the included Pygame-based
+environments is available under [EvoEnv](evoenv.md).
+
+```{toctree}
+:maxdepth: 1
+:hidden:
+:caption: Guides
+
+getting_started
+config_guide
+config_parameter
+evoenv
+```
+
+```{toctree}
+:maxdepth: 2
+:hidden:
+:caption: API – Core
+
+api_core_population
+api_core_individual
+```
+
+```{toctree}
+:maxdepth: 1
+:hidden:
+:caption: API – Representations
+
+api_representation_vector
+api_representation_netvector
+api_representation_evonet
+```
+
+```{toctree}
+:maxdepth: 2
+:hidden:
+:caption: API – Operators
+
+api_operators_strategy
+api_operators_selection
+api_operators_replacement
+api_operators_reproduction
+api_operators_mutation
+api_operators_crossover
+api_operators_evonet_structural_mutation
+```
+
+```{toctree}
+:maxdepth: 2
+:hidden:
+:caption: API – I/O & Utilities
+
+api_utils_loss_functions
+api_utils_benchmarks
+api_utils_plotting
+api_utils_history_logger
+```
+
+```{toctree}
+:maxdepth: 2
+:hidden:
+:caption: Public API
+
+api_public_api
+```
+