Collection of my Reinforcement Learning (RL) practices including DQN, D3QN, and Adaptive Gamma, applied to the Lunar Lander and CartPole environments. 🚀🕹️

Speculative decoding runtime with rejection sampling, adaptive gamma strategy, and provable correctness guarantees. Achieves 1.41x speedup on CPU with Qwen2-0.5B/1.5B pair. Draft model generates candidates, target model verifies in single forward pass. 31/31 tests passing.