ParallelETUCT.cc File Reference

#include "ParallelETUCT.hh"
#include <algorithm>
#include <sys/time.h>

Include dependency graph for ParallelETUCT.cc:

Go to the source code of this file.

Functions
void *	parallelModelLearningStart (void *arg)
void *	parallelSearchStart (void *arg)

---

Detailed Description

Implements my real-time model-based RL architecture which uses UCT with eligiblity traces for planning. The modified version of UCT used is presented in: L. Kocsis and C. Szepesv´ari, "Bandit based monte-carlo planning," in ECML-06. Number 4212 in LNCS. Springer, 2006, pp. 282-293. The real-time architecture is presented in: Hester, Quinlan, and Stone, "A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control", arXiv 1105.1749, 2011.

Author:

Todd Hester

Definition in file ParallelETUCT.cc.

---

Function Documentation

void* parallelModelLearningStart

(

void *

arg

)

Thread that loops, continually updating model with new experiences.

Definition at line 514 of file ParallelETUCT.cc.

void* parallelSearchStart

(

void *

arg

)

Parallel thread that continually does uct search from agent's current state.

Definition at line 1132 of file ParallelETUCT.cc.