Go to the source code of this file.
Classes | |
class | Agent |
class | Classifier |
struct | classPair |
class | Environment |
struct | experience |
class | MDPModel |
class | Model |
struct | modelPair |
class | Planner |
struct | StateActionInfo |
Defines | |
#define | ALLM5TYPES 12 |
#define | AVERAGE 1 |
#define | BEST 3 |
#define | C45TREE 2 |
#define | CMAC_PLANNER 7 |
#define | CONTINUOUS_BONUS 3 |
#define | CONTINUOUS_BONUS_R 5 |
#define | DIFF_AND_NOVEL_BONUS 19 |
#define | DIFF_AND_VISIT_BONUS 16 |
#define | EPSILON 1e-5 |
#define | EPSILONGREEDY 8 |
#define | ET_UCT 4 |
#define | ET_UCT_ACTUAL 14 |
#define | ET_UCT_CORNERS 15 |
#define | ET_UCT_L1 10 |
#define | ET_UCT_WITH_ENV 5 |
#define | EXPLORE_UNKNOWN 0 |
#define | GPREGRESS 13 |
#define | GPTREE 14 |
#define | GREEDY 7 |
#define | LSTMULTI 10 |
#define | LSTSINGLE 11 |
#define | M5ALLMULTI 8 |
#define | M5ALLSINGLE 9 |
#define | M5MULTI 6 |
#define | M5SINGLE 7 |
#define | MBS_VI 20 |
#define | MOD_PRI_SWEEPING 9 |
#define | NN_PLANNER 8 |
#define | NO_EXPLORE 7 |
#define | NOVEL_STATE_BONUS 18 |
#define | PAR_ETUCT_ACTUAL 16 |
#define | PAR_ETUCT_CORNERS 17 |
#define | PARALLEL_ET_UCT 13 |
#define | POLICY_ITERATION 1 |
#define | POMDP_ETUCT 18 |
#define | POMDP_PAR_ETUCT 19 |
#define | PRI_SWEEPING 2 |
#define | RMAX 0 |
#define | SEPARATE 4 |
#define | SINGLETREE 3 |
#define | SLF 1 |
#define | STUMP 5 |
#define | SVM 4 |
#define | SWEEPING_UCT_HYBRID 6 |
#define | TABULAR 0 |
#define | THRESHOLD_BONUS 4 |
#define | THRESHOLD_BONUS_R 6 |
#define | TWO_MODE 1 |
#define | TWO_MODE_PLUS_R 2 |
#define | UCT 3 |
#define | UCT_WITH_ENV 12 |
#define | UCT_WITH_L 11 |
#define | UNVISITED_ACT_BONUS 13 |
#define | UNVISITED_BONUS 11 |
#define | VALUE_ITERATION 0 |
#define | VISITS_CONF 9 |
#define | WEIGHTAVG 2 |
Variables | |
const std::string | comboNames [] |
const std::string | exploreNames [] |
const std::string | modelNames [] |
const std::string | plannerNames [] |
Fundamental declarations for the universal concepts in the reinforcement learning framework.
Definition in file core.hh.
#define ALLM5TYPES 12 |
#define CMAC_PLANNER 7 |
#define CONTINUOUS_BONUS 3 |
#define CONTINUOUS_BONUS_R 5 |
#define DIFF_AND_NOVEL_BONUS 19 |
#define DIFF_AND_VISIT_BONUS 16 |
#define EPSILONGREEDY 8 |
#define ET_UCT_ACTUAL 14 |
#define ET_UCT_CORNERS 15 |
#define ET_UCT_WITH_ENV 5 |
#define EXPLORE_UNKNOWN 0 |
#define M5ALLMULTI 8 |
#define M5ALLSINGLE 9 |
#define MOD_PRI_SWEEPING 9 |
#define NN_PLANNER 8 |
#define NO_EXPLORE 7 |
#define NOVEL_STATE_BONUS 18 |
#define PAR_ETUCT_ACTUAL 16 |
#define PAR_ETUCT_CORNERS 17 |
#define PARALLEL_ET_UCT 13 |
#define POLICY_ITERATION 1 |
#define POMDP_ETUCT 18 |
#define POMDP_PAR_ETUCT 19 |
#define PRI_SWEEPING 2 |
#define SINGLETREE 3 |
#define SWEEPING_UCT_HYBRID 6 |
#define THRESHOLD_BONUS 4 |
#define THRESHOLD_BONUS_R 6 |
#define TWO_MODE_PLUS_R 2 |
#define UCT_WITH_ENV 12 |
#define UCT_WITH_L 11 |
#define UNVISITED_ACT_BONUS 13 |
#define UNVISITED_BONUS 11 |
#define VALUE_ITERATION 0 |
#define VISITS_CONF 9 |
const std::string comboNames[] |
const std::string exploreNames[] |
{ "Explore Unknowns", "Two Modes", "Two Models +R", "Continuous Bonus", "Threshold Bonus", "Continuous Bonus +R", "Threshold Bonus +R", "Greedy", "Epsilon-Greedy", "Visits Confidence", "Type 10", "Unvisited State Bonus", "Type 12", "Unvisited Action Bonus", "Type 14", "Type 15", "Model Diff & Visit Bonus", "Type 17", "FeatDist Bonus", "Model Diff & FeatDist Bonus" }
const std::string modelNames[] |
const std::string plannerNames[] |
{ "Value Iteration", "Policy Iteration", "Prioritized Sweeping", "UCT", "UCT", "UCT", "Sweeping UCT Hybrid", "CMACs", "NN", "Mod. Pri Sweeping", "UCT L=1", "UCT L", "UCT Env", "Parallel UCT", "Real-Valued UCT", "Corner UCT", "Parallel Real-Valued UCT", "Parallel Corner UCT", "Delayed UCT", "Parallel Delayed UCT", "Model Based Simulation - VI" }