simple_rl.experiments package¶
Submodules¶
simple_rl.experiments.ExperimentClass module¶
ExperimentClass.py: Contains the Experiment Class for reproducing RL Experiments.
- Purpose:
- Stores all relevant parameters in experiment directory for easy reproducibility.
- Auto generates plot using chart_utils.
- Can document learning activity.
-
class
simple_rl.experiments.ExperimentClass.
Experiment
(agents, mdp, agent_colors=[], params=None, is_episodic=False, is_markov_game=False, is_lifelong=False, track_disc_reward=False, clear_old_results=True, count_r_per_n_timestep=1, cumulative_plot=True, exp_function='run_agents_on_mdp', dir_for_plot='', experiment_name_prefix='')[source]¶ Bases:
object
-
EXP_PARAM_FILE_NAME
= 'exp_info.txt'¶ Experiment Class for RL Experiments
-
FULL_EXP_FILE_NAME
= 'full_experiment.txt'¶
-
RESULTS_DIR
= '/Users/dabel/Research/simple_rl/docs/sphinx/results/'¶
-
add_experience
(agent, state, action, reward, next_state, time_taken=0)[source]¶ - Args:
- agent (agent OR dict): if self.is_markov_game, contains a dict of agents
- Summary:
- Record any relevant information about this experience.
-
simple_rl.experiments.ExperimentParametersClass module¶
ExperimentParametersClass.py: Contains the ExperimentParameters Class.
Purpose: Bundles all relevant parameters into an object that can be written to a file.