Index

A

act() (simple_rl.agents.AgentClass.Agent method) (simple_rl.agents.BeliefAgentClass.BeliefAgent method) (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method) (simple_rl.agents.DoubleQAgentClass.DoubleQAgent method) (simple_rl.agents.FixedPolicyAgentClass.FixedPolicyAgent method) (simple_rl.agents.QLearningAgentClass.QLearningAgent method) (simple_rl.agents.RMaxAgentClass.RMaxAgent method) (simple_rl.agents.RandomAgentClass.RandomAgent method)

add_experience() (simple_rl.experiments.ExperimentClass.Experiment method) Agent (class in simple_rl.agents.AgentClass) average_data() (in module simple_rl.utils.chart_utils)

B

BeliefAgent (class in simple_rl.agents.BeliefAgentClass)

BeliefSparseSampling (class in simple_rl.planning.BeliefSparseSamplingClass) BoundedRTDP (class in simple_rl.planning.BoundedRTDPClass)

C

choose_mdp() (in module simple_rl.run_experiments)

compute_conf_intervals() (in module simple_rl.utils.chart_utils) compute_single_conf_interval() (in module simple_rl.utils.chart_utils)

D

DelayedQAgent (class in simple_rl.agents.DelayedQAgentClass)

DoubleQAgent (class in simple_rl.agents.DoubleQAgentClass) drange() (in module simple_rl.utils.chart_utils)

E

end_of_episode() (simple_rl.agents.AgentClass.Agent method) (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method) (simple_rl.agents.QLearningAgentClass.QLearningAgent method) (simple_rl.experiments.ExperimentClass.Experiment method) end_of_instance() (simple_rl.experiments.ExperimentClass.Experiment method) (simple_rl.mdp.MDPClass.MDP method)

epsilon_greedy_q_policy() (simple_rl.agents.QLearningAgentClass.QLearningAgent method) evaluate_agent() (in module simple_rl.run_experiments) execute_agent_action() (simple_rl.mdp.MDPClass.MDP method) EXP_PARAM_FILE_NAME (simple_rl.experiments.ExperimentClass.Experiment attribute) Experiment (class in simple_rl.experiments.ExperimentClass) ExperimentParameters (class in simple_rl.experiments.ExperimentParametersClass)

F

features() (simple_rl.mdp.StateClass.State method)

FixedPolicyAgent (class in simple_rl.agents.FixedPolicyAgentClass) FULL_EXP_FILE_NAME (simple_rl.experiments.ExperimentClass.Experiment attribute)

G

get_action_distr() (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method) (simple_rl.agents.QLearningAgentClass.QLearningAgent method) get_actions() (simple_rl.mdp.MDPClass.MDP method) (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) get_agent_avg_cumulative_rew() (simple_rl.experiments.ExperimentClass.Experiment method) get_all_mdps() (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) get_average_reward_func() (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) get_avg_q_value() (simple_rl.agents.DoubleQAgentClass.DoubleQAgent method) get_curr_state() (simple_rl.mdp.MDPClass.MDP method) get_data() (simple_rl.mdp.StateClass.State method) get_gamma() (simple_rl.mdp.MDPClass.MDP method) (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) (simple_rl.planning.ValueIterationClass.ValueIteration method) get_horizon() (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) get_init_state() (simple_rl.mdp.MDPClass.MDP method) (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) get_max_q_action() (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method) (simple_rl.agents.DoubleQAgentClass.DoubleQAgent method) (simple_rl.agents.QLearningAgentClass.QLearningAgent method) (simple_rl.agents.RMaxAgentClass.RMaxAgent method) get_max_q_actions() (simple_rl.planning.ValueIterationClass.ValueIteration method) get_max_q_value() (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method) (simple_rl.agents.DoubleQAgentClass.DoubleQAgent method) (simple_rl.agents.QLearningAgentClass.QLearningAgent method) (simple_rl.agents.RMaxAgentClass.RMaxAgent method) get_mdps() (simple_rl.mdp.MDPDistributionClass.MDPDistribution method)

get_name() (simple_rl.agents.AgentClass.Agent method) get_num_backups_in_recent_run() (simple_rl.planning.ValueIterationClass.ValueIteration method) get_num_feats() (simple_rl.mdp.StateClass.State method) get_num_known_sa() (simple_rl.agents.RMaxAgentClass.RMaxAgent method) get_num_mdps() (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) get_num_state_feats() (simple_rl.mdp.MDPClass.MDP method) get_num_states() (simple_rl.planning.ValueIterationClass.ValueIteration method) get_parameters() (simple_rl.agents.AgentClass.Agent method) (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method) (simple_rl.agents.QLearningAgentClass.QLearningAgent method) (simple_rl.mdp.MDPClass.MDP method) (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) get_prob_of_mdp() (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) get_q_value() (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method) (simple_rl.agents.DoubleQAgentClass.DoubleQAgent method) (simple_rl.agents.QLearningAgentClass.QLearningAgent method) (simple_rl.agents.RMaxAgentClass.RMaxAgent method) (simple_rl.planning.ValueIterationClass.ValueIteration method) get_reward_func() (simple_rl.mdp.MDPClass.MDP method) (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) get_slip_prob() (simple_rl.mdp.MDPClass.MDP method) get_states() (simple_rl.planning.ValueIterationClass.ValueIteration method) get_transition_func() (simple_rl.mdp.MDPClass.MDP method) get_value() (simple_rl.agents.QLearningAgentClass.QLearningAgent method) (simple_rl.planning.ValueIterationClass.ValueIteration method) greedy_q_policy() (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method)

I

is_empty() (simple_rl.utils.additional_datastructures.SimpleRLStack method)

is_known() (simple_rl.agents.RMaxAgentClass.RMaxAgent method) is_terminal() (simple_rl.mdp.StateClass.State method)

L

load_data() (in module simple_rl.utils.chart_utils)

M

main() (in module simple_rl.mdp.MDPDistributionClass) (in module simple_rl.run_experiments) (in module simple_rl.utils.chart_utils) make_markov_game() (in module simple_rl.utils.make_mdp) make_mdp() (in module simple_rl.utils.make_mdp)

make_mdp_distr() (in module simple_rl.utils.make_mdp) make_plots() (in module simple_rl.utils.chart_utils) (simple_rl.experiments.ExperimentClass.Experiment method) MCTS (class in simple_rl.planning.MCTSClass) MDP (class in simple_rl.mdp.MDPClass) MDPDistribution (class in simple_rl.mdp.MDPDistributionClass)

N

NAME (simple_rl.agents.FixedPolicyAgentClass.FixedPolicyAgent attribute)

P

parse_args() (in module simple_rl.run_experiments) (in module simple_rl.utils.chart_utils) peek() (simple_rl.utils.additional_datastructures.SimpleRLStack method) plan() (simple_rl.planning.BoundedRTDPClass.BoundedRTDP method) (simple_rl.planning.MCTSClass.MCTS method) (simple_rl.planning.ValueIterationClass.ValueIteration method) plan_from_state() (simple_rl.planning.BeliefSparseSamplingClass.BeliefSparseSampling method) Planner (class in simple_rl.planning.PlannerClass) play_markov_game() (in module simple_rl.run_experiments)

plot() (in module simple_rl.utils.chart_utils) policy() (simple_rl.agents.AgentClass.Agent method) (simple_rl.agents.BeliefAgentClass.BeliefAgent method) (simple_rl.planning.BoundedRTDPClass.BoundedRTDP method) (simple_rl.planning.MCTSClass.MCTS method) (simple_rl.planning.ValueIterationClass.ValueIteration method) pop() (simple_rl.utils.additional_datastructures.SimpleRLStack method) print_value_func() (simple_rl.planning.ValueIterationClass.ValueIteration method) push() (simple_rl.utils.additional_datastructures.SimpleRLStack method)

Q

QLearningAgent (class in simple_rl.agents.QLearningAgentClass)

R

RandomAgent (class in simple_rl.agents.RandomAgentClass) remove_mdp() (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) remove_mdps() (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) reproduce_from_exp_file() (in module simple_rl.run_experiments) reset() (simple_rl.agents.AgentClass.Agent method) (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method) (simple_rl.agents.DoubleQAgentClass.DoubleQAgent method) (simple_rl.agents.QLearningAgentClass.QLearningAgent method) (simple_rl.agents.RMaxAgentClass.RMaxAgent method) (simple_rl.mdp.MDPClass.MDP method)

RESULTS_DIR (simple_rl.experiments.ExperimentClass.Experiment attribute) RMaxAgent (class in simple_rl.agents.RMaxAgentClass) run() (simple_rl.planning.BeliefSparseSamplingClass.BeliefSparseSampling method) run_agents_lifelong() (in module simple_rl.run_experiments) run_agents_on_mdp() (in module simple_rl.run_experiments) run_sample_trial() (simple_rl.planning.BoundedRTDPClass.BoundedRTDP method) run_single_agent_on_mdp() (in module simple_rl.run_experiments) run_single_belief_agent_on_pomdp() (in module simple_rl.run_experiments) run_vi() (simple_rl.planning.ValueIterationClass.ValueIteration method)

S

sample() (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) set_gamma() (simple_rl.mdp.MDPClass.MDP method) (simple_rl.mdp.MDPDistributionClass.MDPDistribution method) set_name() (simple_rl.agents.AgentClass.Agent method) set_policy() (simple_rl.agents.FixedPolicyAgentClass.FixedPolicyAgent method) set_q_function() (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method) set_slip_prob() (simple_rl.mdp.MDPClass.MDP method) set_step_cost() (simple_rl.mdp.MDPClass.MDP method) set_terminal() (simple_rl.mdp.StateClass.State method) set_vmax() (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method) simple_rl (module) simple_rl.agents (module) simple_rl.agents.AgentClass (module) simple_rl.agents.BeliefAgentClass (module) simple_rl.agents.DelayedQAgentClass (module) simple_rl.agents.DoubleQAgentClass (module) simple_rl.agents.FixedPolicyAgentClass (module) simple_rl.agents.QLearningAgentClass (module) simple_rl.agents.RandomAgentClass (module) simple_rl.agents.RMaxAgentClass (module) simple_rl.experiments (module)

simple_rl.experiments.ExperimentClass (module) simple_rl.experiments.ExperimentParametersClass (module) simple_rl.mdp (module) simple_rl.mdp.MDPClass (module) simple_rl.mdp.MDPDistributionClass (module) simple_rl.mdp.StateClass (module) simple_rl.planning (module) simple_rl.planning.BeliefSparseSamplingClass (module) simple_rl.planning.BoundedRTDPClass (module) simple_rl.planning.MCTSClass (module) simple_rl.planning.PlannerClass (module) simple_rl.planning.ValueIterationClass (module) simple_rl.run_experiments (module) simple_rl.tasks (module) simple_rl.utils (module) simple_rl.utils.additional_datastructures (module) simple_rl.utils.chart_utils (module) simple_rl.utils.make_mdp (module) SimpleRLStack (class in simple_rl.utils.additional_datastructures) size() (simple_rl.utils.additional_datastructures.SimpleRLStack method) soft_max_policy() (simple_rl.agents.QLearningAgentClass.QLearningAgent method) State (class in simple_rl.mdp.StateClass)

U

update() (simple_rl.agents.DelayedQAgentClass.DelayedQAgent method) (simple_rl.agents.DoubleQAgentClass.DoubleQAgent method) (simple_rl.agents.QLearningAgentClass.QLearningAgent method) (simple_rl.agents.RMaxAgentClass.RMaxAgent method)

V

ValueIteration (class in simple_rl.planning.ValueIterationClass)

W

write_datum_to_file() (simple_rl.experiments.ExperimentClass.Experiment method)

write_exp_info_to_file() (simple_rl.experiments.ExperimentClass.Experiment method)