Metadata-Version: 2.4
Name: rl-softmax-policy
Version: 0.1.0
Summary: Softmax-based (Boltzmann) action selection strategy for Reinforcement Learning.
Author: Afi Prasla
License: MIT
License-File: LICENSE
Keywords: boltzmann,policy,reinforcement-learning,rl,softmax
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.8
Description-Content-Type: text/markdown

# rl-softmax-policy

Implements **Softmax (Boltzmann) Action Selection**, a probabilistic exploration strategy for Reinforcement Learning agents.

## Example Usage
```python
from rlsoftmaxpolicy_colab import softmax_action_selection

q_values = [1.0, 2.0, 3.0]
temperature = 0.8
action = softmax_action_selection(q_values, temperature)
print('Selected action:', action)
```

Author: Afi Prasla
