You can deploy this model and start earning money today!

mohamednabil500/
ppo-space-invaders-10M-expert

Name: ppo-space-invaders-10M-expert
Availability: InStock

reinforcement-learning

Views

No views yet

PPO Expert Agent for ALE/SpaceInvaders-v5 (10M Steps)

This is a Proximal Policy Optimization (PPO) agent trained on Atari Space Invaders (v5) using a vectorized environment setup.

Training Details

Algorithm: PPO
Environment: ALE/SpaceInvaders-v5 (with sticky actions)
Total Timesteps: 10,000,000
Frame Stacking: 4 frames
Terminal on Life Loss: True (during training)

Performance

Peak Score observed: 615.0
Average Reward (approx): ~300-450 range at 10M steps.
Behavior: Learned to clear multiple waves, use shields for cover, and target the Mystery Ship.

Usage

python

import torch
# Assumes you have the ActorCritic class defined in your script
config = Config() # Using your existing Config class
model = ActorCritic(input_channels=4, action_dim=6) # Space Invaders has 6 actions
model.load_state_dict(torch.load('ppo_final_10M.pt', map_location='cpu'))
model.eval()

mohamednabil500/ppo-space-invaders-10M-expert

PPO Expert Agent for ALE/SpaceInvaders-v5 (10M Steps)

Training Details

Performance

Usage

mohamednabil500/
ppo-space-invaders-10M-expert