|
bitrl & cuberl Documentation
Simulation engine for reinforcement learning agents
|
Classes | |
| struct | SamplingResult |
Functions | |
| SamplingResult | run_epsilon_greedy (MultiArmedBandits &env, real_t eps) |
| SamplingResult | run_thompson_sampling (MultiArmedBandits &env) |
Variables | |
| uint_t | N_EPISODES = 1000 |
| real_t | EPS = 0.2 |
| SamplingResult rl_example_2::run_epsilon_greedy | ( | MultiArmedBandits & | env, |
| real_t | eps | ||
| ) |
| SamplingResult rl_example_2::run_thompson_sampling | ( | MultiArmedBandits & | env | ) |
| real_t rl_example_2::EPS = 0.2 |
| uint_t rl_example_2::N_EPISODES = 1000 |