diff --git a/deepdip/deepdip_stable-baselines.py b/deepdip/deepdip_stable-baselines.py index 1a235da..4f146e0 100644 --- a/deepdip/deepdip_stable-baselines.py +++ b/deepdip/deepdip_stable-baselines.py @@ -224,9 +224,9 @@ def plot_rewards(): if __name__ == '__main__': env = make_env(gym_env_id) - #train(env, total_timesteps) - #evaluate(env, evaluate_timesteps) - #plot_results(log_dir) + train(env, total_timesteps) + evaluate(env, evaluate_timesteps) + plot_results(log_dir) plot_rewards() env.close() diff --git a/gym-diplomacy/gym_diplomacy/envs/diplomacy_strategy_env.py b/gym-diplomacy/gym_diplomacy/envs/diplomacy_strategy_env.py index 08e6687..ff90596 100644 --- a/gym-diplomacy/gym_diplomacy/envs/diplomacy_strategy_env.py +++ b/gym-diplomacy/gym_diplomacy/envs/diplomacy_strategy_env.py @@ -26,7 +26,7 @@ ### CONSTANTS NUMBER_OF_ACTIONS = 3 MAPS = ['mini', 'small', 'three', 'standard'] -CURRENT_MAP = MAPS[3] +CURRENT_MAP = MAPS[2] PLAYERS = {'mini':2, 'small':2, 'three':3, 'standard':7} NUMBER_OF_PLAYERS = PLAYERS[CURRENT_MAP] REGIONS = {'mini':10, 'small':19, 'three':37, 'standard':121}