RLPy
A framework for sequential decision-making experiments, focused on value-function-based reinforcement learning and the core algorithms. Published in JMLR and distributed under the 3-Clause BSD License.
View on GitHub
Intruder Monitoring Domain
Formulated as an MDP, the task is to guard danger zones using cameras (O) so that if an intruder (▶) moves into a danger zone, at least one camera is pointing at that location. An episode ends after 1000 steps. The initial grids of cameras and intruders are highlighted with the same color code.
Download code
gprof2dot with total time
A modified gprof2dot.py that adds the program's total running time as a node in the output graph. Works with pstats files produced by cProfile.