增强学习深圳俄罗斯方块

SZ-Tetris is the "hard core" of Tetris (only "S" and "Z" tetrominoes are coming, making the problem more challenging). It is used as a reinforcement learning benchmark. This code was used for experiments in the paper "SZ-Tetris as a Benchmark for Studying Key Problems of Reinforcement Learning" by I. Szita and Cs. Szepesvári, on the Machine Learning and Games workshop of ICML"10.

sztetris_v0.0
.classpath
.DS_Store
.project
.settings
BI_lambda0.0000.txt
BI_lambda0.0000_eval.txt
BI_lambda0.5000.txt
BI_lambda0.5000_eval.txt
BI_lambda0.6667.txt
BI_lambda0.6667_eval.txt
BI_lambda0.7500.txt
BI_lambda0.7500_eval.txt
BI_lambda0.8000.txt
BI_lambda0.8000_eval.txt
BI_lambda0.8333.txt
BI_lambda0.8333_eval.txt
BI_lambda0.8571.txt
BI_lambda0.8571_eval.txt
BI_lambda0.8750.txt
BI_lambda0.8750_eval.txt
BI_lambda0.8889.txt
BI_lambda0.8889_eval.txt
BI_lambda0.9000.txt
BI_lambda0.9000_eval.txt
BI_lambda1.0000.txt
BI_lambda1.0000_eval.txt
build-before-profiler.xml
build.xml
build_eclipse.xml
build_netbeans.xml
CE_BI_run00_eval.txt
CE_BI_run00_forhuman.txt
CE_BI_run00_formatlab.txt
CE_BI_run01_eval.txt
CE_BI_run01_forhuman.txt
CE_BI_run01_formatlab.txt
CE_BI_run02_eval.txt
CE_BI_run02_forhuman.txt
CE_BI_run02_formatlab.txt
CE_BI_run03_eval.txt
CE_BI_run03_forhuman.txt
CE_BI_run03_formatlab.txt
CE_BI_run04_eval.txt
CE_BI_run04_forhuman.txt
CE_BI_run04_formatlab.txt
CE_BI_run05_forhuman.txt
CE_BI_run05_formatlab.txt
CE_BI_run06_forhuman.txt
CE_BI_run06_formatlab.txt
CE_BI_run07_forhuman.txt
CE_BI_run07_formatlab.txt
CE_ST_run00_eval.txt
CE_ST_run00_forhuman.txt
CE_ST_run00_formatlab.txt
CE_ST_run01_eval.txt
CE_ST_run01_forhuman.txt
CE_ST_run01_formatlab.txt
CE_ST_run02_eval.txt
CE_ST_run02_forhuman.txt
CE_ST_run02_formatlab.txt
CE_ST_run03_eval.txt
CE_ST_run03_forhuman.txt
CE_ST_run03_formatlab.txt
CE_ST_run04_eval.txt
CE_ST_run04_forhuman.txt
CE_ST_run04_formatlab.txt
CE_ST_run05_forhuman.txt
CE_ST_run05_formatlab.txt
CE_ST_run06_forhuman.txt
CE_ST_run06_formatlab.txt
CE_ST_run07_forhuman.txt
CE_ST_run07_formatlab.txt
CE_XT_run00_eval.txt
CE_XT_run00_forhuman.txt
CE_XT_run00_formatlab.txt
CE_XT_run01_eval.txt
CE_XT_run01_forhuman.txt
CE_XT_run01_formatlab.txt
CE_XT_run02_eval.txt
CE_XT_run02_forhuman.txt
CE_XT_run02_formatlab.txt
CE_XT_run03_eval.txt
CE_XT_run03_forhuman.txt
CE_XT_run03_formatlab.txt
CE_XT_run04_eval.txt
CE_XT_run04_forhuman.txt
CE_XT_run04_formatlab.txt
CE_XT_run05_forhuman.txt
CE_XT_run05_formatlab.txt
CE_XT_run06_forhuman.txt
CE_XT_run06_formatlab.txt
dist
jars
lib
m
manifest.mf
nbproject
run000.txt
run001.txt
run002.txt
run003.txt
run004.txt
run005.txt
run006.txt
run007.txt
run008.txt
run009.txt
run010.txt
src
test