129130131132133134135136137138
@Override public void agent_end(double reward) { current_episode.addTransiton(last_state, last_action, null, reward); Agent agent = new GDLAlgorithmAgent(my_role); algorithm.learnEpisode(current_episode, agent); algorithm.save(); }
173174175176177178179180181182183
{ break; } List<Agent> agents = new ArrayList<Agent>(); Agent learner = new GDLAlgorithmAgent(my_role); for(String role : all_roles) { agents.add(new GDLAlgorithmAgent(role)); } algorithm.exploreFromEpisode(state, current_episode, agents, learner);