chore: cleanup and HPC integration

configs/default_ppo.yaml

@@ -1,48 +0,0 @@
-# PPO Training Configuration Template
-#
-# This file provides an example configuration for PPO training.
-# Copy this file and modify it for your specific experiments.
-#
-# Usage:
-#   python src/train.py --config-path configs/my_config.yaml
-# Or override specific parameters:
-#   python src/train.py --learning-rate 0.001 --num-envs 32
-
-# Experiment settings
-exp_name: "brittle_star_ppo"
-seed: 1
-
-# Tracking settings
-track: false  # Set to true to enable WandB logging
-wandb_project_name: "PPO-Modularity"
-wandb_entity: "SEL3-2026-Groep-4"  # Set to your WandB username or team name
-
-# Model saving
-save_model: true
-checkpoint_frequency: 100  # Save checkpoint every N iterations (0 = no checkpoints)
-
-# Environment settings
-num_envs: 16
-
-# Training hyperparameters
-total_timesteps: 10000000
-learning_rate: 0.00025
-num_steps: 128
-anneal_lr: true
-
-# PPO specific
-gamma: 0.99
-gae_lambda: 0.95
-num_minibatches: 4
-update_epochs: 4
-norm_adv: true
-clip_coef: 0.1
-clip_vloss: true
-ent_coef: 0.01
-vf_coef: 0.5
-max_grad_norm: 0.5
-target_kl: null
-
-# Hardware
-cuda: true
-torch_deterministic: true

configs/dev_test.yaml

@@ -1,42 +0,0 @@
-# Quick Development/Testing Configuration
-#
-# Fast configuration for development and testing with short runs.
-
-# Experiment settings
-exp_name: "brittle_star_dev_test"
-seed: 123
-
-# Tracking settings - IMPORTANT: Set your own wandb_entity!
-track: true
-wandb_project_name: "PPO-Modularity-Dev"
-wandb_entity: "SEL3-2026-Groep-4"  # ⚠️  SET THIS TO YOUR WANDB USERNAME OR TEAM
-
-# Model saving
-save_model: true
-checkpoint_frequency: 10  # More frequent checkpoints for testing
-
-# Environment settings
-num_envs: 4  # Smaller for faster iteration
-
-# Training hyperparameters - Fast/testing
-total_timesteps: 100000  # Short run for testing
-learning_rate: 0.001  # Higher learning rate for faster learning
-num_steps: 64  # Shorter rollouts
-anneal_lr: true
-
-# PPO specific - Optimized for quick results
-gamma: 0.99
-gae_lambda: 0.95
-num_minibatches: 2
-update_epochs: 2  # Fewer epochs for speed
-norm_adv: true
-clip_coef: 0.1
-clip_vloss: true
-ent_coef: 0.02  # Higher entropy for exploration
-vf_coef: 0.5
-max_grad_norm: 0.5
-target_kl: null
-
-# Hardware
-cuda: true
-torch_deterministic: true

configs/example.yaml

@@ -1,4 +0,0 @@
-morphology:
-  segments_per_arm: [4, 4]
-  use_p_control: true
-  use_torque_control: false

configs/hpc/smoke_test.yaml

@@ -1,11 +0,0 @@
-# Minimal config to verify HPC setup is functional.
-# Run with: python scripts/train.py --config-path configs/hpc/smoke_test.yaml
-exp_name: "hpc_smoke_test"
-seed: 0
-track: false           # Test WandB integration
-capture_video: false  # No rendering for smoke test
-save_model: true      # Test the end-of-training save routine
-num_envs: 512
-total_timesteps: 65536
-num_steps: 128
-cuda: true

configs/hpc/wandb_expand.yaml

@@ -1,10 +0,0 @@
-exp_name: "explained_var_fun_more_steps"
-seed: 42
-track: true
-wandb_project_name: "LET-THERE-BE-MORE-LOGGING"
-wandb_entity: "SEL3-2026-Groep-4"
-
-num_envs: 16
-num_steps: 256
-total_timesteps: 50000
-cuda: true

configs/hpc/wandb_test.yaml

@@ -1,11 +0,0 @@
-# Configuration to verify WandB online tracking
-exp_name: "hpc_wandb_verification"
-seed: 42
-track: true               # Enabled for testing WandB
-wandb_project_name: "PPO-Modularity"
-wandb_entity: "SEL3-2026-Groep-4"
-
-num_envs: 128
-total_timesteps: 50000    # Short run for quick verification
-num_steps: 128
-cuda: true

configs/personal_template.yaml

@@ -1,40 +0,0 @@
-# Personal Configuration Example for Team Member
-#
-# Copy this template and customize for your personal experiments
-
-# Experiment settings - PERSONALIZE THESE
-exp_name: "YOUR_NAME_experiment_v1"  # ⚠️ Change YOUR_NAME 
-seed: 42
-
-# WandB settings - ⚠️ IMPORTANT: Set your credentials!
-track: true  # Enable WandB tracking
-wandb_project_name: "PPO-Modularity"
-wandb_entity: "SEL3-2026-Groep-4"  # ⚠️ CHANGE THIS to your WandB username/team
-
-# Quick experiment settings (modify as needed)
-total_timesteps: 500000  # 500K for quick results
-num_envs: 8
-learning_rate: 0.0005
-num_steps: 128
-
-# Model saving
-save_model: true  
-checkpoint_frequency: 25  # Save checkpoints frequently
-
-# Standard PPO settings (usually don't need to change)
-gamma: 0.99
-gae_lambda: 0.95
-num_minibatches: 4
-update_epochs: 4
-norm_adv: true
-clip_coef: 0.2
-clip_vloss: true
-ent_coef: 0.01
-vf_coef: 0.5
-max_grad_norm: 0.5
-target_kl: null
-anneal_lr: true
-
-# Hardware
-cuda: true
-torch_deterministic: true

configs/production_training.yaml

@@ -1,42 +0,0 @@
-# Production Training Configuration
-#
-# Full-scale training configuration for production runs
-# with wandb logging enabled.
-
-# Experiment settings
-exp_name: "brittle_star_production_training"
-seed: 42
-
-# Tracking
-track: true
-capture_video: false
-wandb_project_name: "PPO-Modularity"
-wandb_entity: "SEL3-2026-Groep-4"
-
-# Model saving
-save_model: true
-checkpoint_frequency: 100  # Save checkpoint every 100 iterations
-
-# Environment settings
-num_envs: 512
-
-# Training hyperparameters
-total_timesteps: 50000000
-num_steps: 256
-num_minibatches: 4
-update_epochs: 4
-
-learning_rate: 2.5e-4
-anneal_lr: true
-gamma: 0.99
-gae_lambda: 0.95
-clip_coef: 0.1
-clip_vloss: true
-ent_coef: 0.01
-vf_coef: 0.5
-max_grad_norm: 0.5
-target_kl: null
-
-# Hardware
-cuda: true
-torch_deterministic: true