working version of fractions PPO model and decision tree model

sandbox/fractions/run_al_fractions.py

sandbox/fractions/run_ppo_fractions.py

sandbox/multicolumn/run_cobweb_multi.py

sandbox/multicolumn/run_decision_tree_multi-v1.py

sandbox/multicolumn/run_dual_decision_tree_multi.py

sandbox/multicolumn/run_dual_ppo.py

sandbox/multicolumn/run_ppo_multi-v0.py

sandbox/multicolumn/run_ppo_multi-v1.py

sandbox/multicolumn/run_ppo_multi-v2.py

sandbox/multicolumn/run_ppo_multi-v3.py

sandbox/multicolumn/run_single_decision_tree_multi.py

sandbox/multicolumn/run_single_dqn.py

tutorenvs/__init__.py

tutorenvs/fractions.py

tutorenvs/multicolumn.py

tutorenvs/utils.py