|
CRAAM
2.0.0
Robust and Approximate Markov Decision Processes
|
A deterministic policy that chooses actions according to the provided action index. More...
#include <Simulation.hpp>
Public Types | |
| using | State = typename Sim::State |
| using | Action = typename Sim::Action |
Public Member Functions | |
| DeterministicPolicy (const Sim &sim, indvec actions) | |
| Initializes randomized polices, transition probabilities for each state. More... | |
| Action | operator() (State state) |
| Returns a random action. | |
Protected Attributes | |
| indvec | actions |
| List of which action to take in which state. | |
| const Sim & | sim |
| simulator reference | |
A deterministic policy that chooses actions according to the provided action index.
State must be convertible to a long index; that is must support (explicit) operator long Actions also have to be indexed. See the definition of simulate.
|
inline |
Initializes randomized polices, transition probabilities for each state.
| sim | Simulator used with the policy. The reference is retained, the object should not be deleted |
| actions | Index of action to take for each state |
1.8.13