def plot_learning(df: pd.DataFrame,
sweep_vars: Sequence[str] = None) -> gg.ggplot:
"""Plots the average regret through time."""
p = plotting.plot_regret_learning(df,
sweep_vars=sweep_vars,
max_episode=sweep.NUM_EPISODES)
return bandit_learning_format(p)
def plot_learning(df: pd.DataFrame,
sweep_vars: Optional[Sequence[str]] = None) -> gg.ggplot:
"""Simple learning curves for catch."""
p = plotting.plot_regret_learning(
df, sweep_vars=sweep_vars, max_episode=sweep.NUM_EPISODES)
p += gg.geom_hline(
gg.aes(yintercept=BASE_REGRET), linetype='dashed', alpha=0.4, size=1.75)
return p
def plot_learning(df: pd.DataFrame,
sweep_vars: Sequence[Text] = None) -> gg.ggplot:
"""Plots the average regret through time."""
p = plotting.plot_regret_learning(
df, sweep_vars=sweep_vars, max_episode=sweep.NUM_EPISODES)
p += gg.geom_hline(gg.aes(yintercept=BASE_REGRET),
linetype='dashed', alpha=0.4, size=1.75)
return p
def plot_learning(df: pd.DataFrame,
sweep_vars: Sequence[Text] = None,
group_col: Text = 'noise_scale') -> gg.ggplot:
"""Plots the average regret through time."""
p = plotting.plot_regret_learning(
df_in=df, group_col=group_col, sweep_vars=sweep_vars,
max_episode=sweep.NUM_EPISODES)
return bandit_analysis.bandit_learning_format(p)
def plot_learning(df: pd.DataFrame,
sweep_vars: Sequence[str] = None) -> gg.ggplot:
"""Simple learning curves for cartpole."""
df = cartpole_preprocess(df)
p = plotting.plot_regret_learning(
df, sweep_vars=sweep_vars, max_episode=NUM_EPISODES)
p += gg.geom_hline(gg.aes(yintercept=BASE_REGRET),
linetype='dashed', alpha=0.4, size=1.75)
return p
def plot_learning(df: pd.DataFrame,
sweep_vars: Optional[Sequence[str]] = None,
group_col: str = 'noise_scale') -> gg.ggplot:
"""Plots the average regret through time."""
p = plotting.plot_regret_learning(
df_in=df, group_col=group_col, sweep_vars=sweep_vars,
max_episode=sweep.NUM_EPISODES)
p += gg.geom_hline(gg.aes(yintercept=catch_analysis.BASE_REGRET),
linetype='dashed', alpha=0.4, size=1.75)
return p
def plot_learning(df: pd.DataFrame,
sweep_vars: Sequence[str] = None) -> gg.ggplot:
"""Plots the average regret through time by optimal_horizon."""
df = dc_preprocess(df_in=df)
p = plotting.plot_regret_learning(
df_in=df,
group_col='optimal_horizon',
sweep_vars=sweep_vars,
max_episode=sweep.NUM_EPISODES
)
p += gg.geom_hline(gg.aes(yintercept=BASE_REGRET),
linetype='dashed', alpha=0.4, size=1.75)
p += gg.coord_cartesian(ylim=(0, 0.1))
return p
def plot_learning(df: pd.DataFrame,
sweep_vars: Sequence[Text] = None,
group_col: Text = 'noise_scale') -> gg.ggplot:
"""Plots the average regret through time."""
df = mountain_car_analysis.mountain_car_preprocess(df)
p = plotting.plot_regret_learning(df_in=df,
group_col=group_col,
sweep_vars=sweep_vars,
max_episode=sweep.NUM_EPISODES)
p += gg.geom_hline(gg.aes(yintercept=mountain_car_analysis.BASE_REGRET),
linetype='dashed',
alpha=0.4,
size=1.75)
return p
def plot_learning(df: pd.DataFrame,
sweep_vars: Sequence[str] = None,
group_col: str = 'delay') -> gg.ggplot:
"""Plots the average regret through time."""
df = mdpp_preprocess_delay(df)
p = plotting.plot_regret_learning(df_in=df,
group_col=group_col,
sweep_vars=sweep_vars,
max_episode=sweep.NUM_EPISODES)
p += gg.geom_hline(gg.aes(yintercept=BASE_REGRET),
linetype='dashed',
alpha=0.4,
size=1.75)
return p
