|
@@ -2,16 +2,20 @@ Directory Structure
|
|
|
------
|
|
------
|
|
|
.
|
|
.
|
|
|
└── Search-based Planning
|
|
└── Search-based Planning
|
|
|
- ├── bfs.py # breadth-first searching
|
|
|
|
|
- ├── dfs.py # depth-first searching
|
|
|
|
|
- ├── dijkstra.py # dijkstra's algorithm
|
|
|
|
|
- └── a_star.py # a* algorithm
|
|
|
|
|
|
|
+ ├── bfs.py # breadth-first
|
|
|
|
|
+ ├── dfs.py # depth-first
|
|
|
|
|
+ ├── dijkstra.py # dijkstra's
|
|
|
|
|
+ ├── a_star.py # a*
|
|
|
|
|
+ ├── queue.py # FIFO, FILO, Priority queues
|
|
|
|
|
+ ├── env.py # environment: working space
|
|
|
|
|
+ ├── motion_model.py # motion model, feasible input
|
|
|
|
|
+ ├── tools.py # animation, figure generation ...
|
|
|
└── Stochastic Shortest Path
|
|
└── Stochastic Shortest Path
|
|
|
- ├── value_iteration.py # value iteration
|
|
|
|
|
- ├── policy_iteration.py # policy iteration
|
|
|
|
|
- ├── Q-value_iteration.py # Q-value iteration
|
|
|
|
|
- └── Q-policy_iteration.py # Q-policy iteration
|
|
|
|
|
|
|
+ ├── value_iteration.py # value iteration
|
|
|
|
|
+ ├── policy_iteration.py # policy iteration
|
|
|
|
|
+ ├── Q-value_iteration.py # Q-value iteration
|
|
|
|
|
+ └── Q-policy_iteration.py # Q-policy iteration
|
|
|
└── Sampling-based Planning
|
|
└── Sampling-based Planning
|
|
|
- ├── Sarsa.py # SARSA : on-policy TD control
|
|
|
|
|
- └── Q-learning.py # Q-learning : off-policy TD control
|
|
|
|
|
|
|
+ ├── Sarsa.py # SARSA : on-policy TD control
|
|
|
|
|
+ └── Q-learning.py # Q-learning : off-policy TD control
|
|
|
└── Model-free Control
|
|
└── Model-free Control
|