taxi-v3-learning
What it is
A research repository implementing two Hierarchical Reinforcement Learning algorithms (SMDP Q-Learning and Intra Option Q-Learning) for the OpenAI Gym Taxi-v3 environment. It compares these learned agents against hardcoded baselines to demonstrate the effectiveness of state compression and sample efficiency.
The problem it solves
Lack of comparative benchmarks for specific hierarchical RL variants (SMDP vs. Intra Option) on standard discrete environments like Taxi-v3.
What you could use it for
- Comparing hierarchical RL algorithms on discrete grid-world tasks
- Demonstrating the impact of state compression on Q-learning performance
- Educational reference for implementing SMDP and Intra Option Q-Learning
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.