No good implementation
Algorithm's net:
No good implementation
Algorithm's net:
- SAC | OpenAI
- Environments in OpenAI
- Deep-Reinforcement-Learning-Hands-On-Second-Edition
- Policy Gradient Algorithms | Lilian Weng's Blog
- DATASETS & DATALOADERS | PyTorch
- SAVING AND LOADING MODELS | PyTorch
- PROBABILITY DISTRIBUTIONS - TORCH.DISTRIBUTIONS | PyTorch
- SOURCE CODE FOR TORCH.DISTRIBUTIONS.NORMAL | PyTorch
- SOFTPLUS | PyTorch
- AUTOGRAD MECHANICS | PyTorch
- Reparameterization Trick
- SAC implementation | TDS, (code)
- Probability density function | Wikipedia
- Change of variables: Apply tanh to the Gaussian samples | math.stackexchange.com