Merge pull request #61 from rk1a/improve-world-seeding

Improve world seeding and config handling

.gitignore

@@ -79,6 +79,7 @@ newworld/
 !/mods/rewards/
 !/mods/treechop_shaped_v*/
 /worlds
+/configs
 /world/
 /clientmods/*
 !/clientmods/rewards/

minetester/minetest_env.py

@@ -9,10 +9,16 @@
 import matplotlib.pyplot as plt
 import numpy as np
 import zmq
-
-from minetester.utils import (KEY_MAP, pack_pb_action, start_minetest_client,
- start_minetest_server, start_xserver,
- unpack_pb_obs)
+from minetester.utils import (
+ KEY_MAP,
+ pack_pb_action,
+ start_minetest_client,
+ start_minetest_server,
+ read_config_file,
+ write_config_file,
+ unpack_pb_obs,
+ start_xserver,
+)
 
 import pkg_resources
 
@@ -30,7 +36,8 @@ def __init__(
  config_path: Optional[os.PathLike] = None,
  display_size: Tuple[int, int] = default_display_size,
  fov: int = 72,
- seed: Optional[int] = None,
+ base_seed: int = 0,
+ world_seed: Optional[int] = None,
  start_minetest: bool = True,
  game_id: str = "minetest",
  client_name: str = "minetester",
@@ -45,19 +52,15 @@ def __init__(
  ):
  self.unique_env_id = str(uuid.uuid4())
 
- # Seed the environment
- if seed is not None:
- self.seed(seed)
-
  # Graphics settings
  self._set_graphics(headless, display_size, fov) 
 
  # Define action and observation space
  self._configure_spaces()
 
  # Define Minetest paths
- self._set_artefact_dirs(artefact_dir, world_dir, config_path, config_dict) #Stores minetest artefacts and outputs
- self._set_minetest_dirs(minetest_root) #Stores actual minetest dirs and executable
+ self._set_artefact_dirs(artefact_dir, world_dir, config_path) # Stores minetest artefacts and outputs
+ self._set_minetest_dirs(minetest_root)  # Stores actual minetest dirs and executable
 
  # Whether to start minetest server and client
  self.start_minetest = start_minetest
@@ -85,6 +88,19 @@ def __init__(
  self.render_fig = None
  self.render_img = None
 
+ # Seed the environment
+ self.base_seed = base_seed
+ self.world_seed = world_seed
+ # If no world_seed is provided
+ # seed the world with a random seed
+ # generated by the RNG from base_seed
+ self.reseed_on_reset = world_seed is None
+ self.seed(self.base_seed)
+
+ # Write minetest.conf
+ self.config_dict = config_dict
+ self._write_config()
+
  # Configure logging
  logging.basicConfig(
  filename=os.path.join(self.log_dir, f"env_{self.unique_env_id}.log"),
@@ -102,7 +118,7 @@ def __init__(
  self.servermods += ["rewards"] # require the server rewards mod
  self._enable_servermods()
  else:
- self.clientmods += ["rewards"] # require the client rewards mod
+ self.clientmods += ["rewards"] # require the client rewards med
  # add client mod names in case they entail a server side component
  self.servermods += clientmods
  self._enable_clientmods()
@@ -178,7 +194,7 @@ def _set_minetest_dirs(self, minetest_root):
  "mouse_cursor_white_16x16.png",
  )
 
- def _set_artefact_dirs(self, artefact_dir, world_dir, config_path, config_dict):
+ def _set_artefact_dirs(self, artefact_dir, world_dir, config_path):
  if artefact_dir is None:
  self.artefact_dir = os.path.join(os.getcwd(), "artefacts")
  else:
@@ -204,10 +220,6 @@ def _set_artefact_dirs(self, artefact_dir, world_dir, config_path, config_dict):
  os.makedirs(self.log_dir, exist_ok=True)
  os.makedirs(self.media_cache_dir, exist_ok=True)
 
- # Write minetest.conf
- self.config_dict = config_dict
- self._write_config()
-
  def _enable_clientmods(self):
  clientmods_folder = os.path.realpath(
  os.path.join(os.path.dirname(self.minetest_executable), "../clientmods"),
@@ -305,7 +317,7 @@ def _check_world_dir(self):
 
  def _delete_world(self):
  if os.path.exists(self.world_dir):
- shutil.rmtree(self.world_dir)
+ shutil.rmtree(self.world_dir, ignore_errors=True)
 
  def _check_config_path(self):
  if self.config_path is None:
@@ -319,59 +331,56 @@ def _delete_config(self):
  os.remove(self.config_path)
 
  def _write_config(self):
- with open(self.config_path, "w") as config_file:
- # Update default settings
- # TODO load these values from custom minetest config
- config_file.write("mute_sound = true\n")
- config_file.write("show_debug = false\n")
- config_file.write("enable_client_modding = true\n")
- # config_file.write("video_driver = null\n")
- # config_file.write("enable_shaders = false\n")
- config_file.write("csm_restriction_flags = 0\n")
- config_file.write("enable_mod_channels = true\n")
- config_file.write("server_map_save_interval = 1000000\n")
- config_file.write("profiler_print_interval = 0\n")
- config_file.write("active_block_range = 2\n")
- config_file.write("abm_time_budget = 0.01\n")
- config_file.write("abm_interval = 0.1\n")
- config_file.write("active_block_mgmt_interval = 4.0\n")
- config_file.write("server_unload_unused_data_timeout = 1000000\n")
- config_file.write("client_unload_unused_data_timeout = 1000000\n")
- config_file.write("debug_log_level = verbose\n")
- config_file.write("full_block_send_enable_min_time_from_building = 0.\n")
- config_file.write("max_block_send_distance = 100\n")
- config_file.write("max_block_generate_distance = 100\n")
- config_file.write("num_emerge_threads = 0\n")
- config_file.write("emergequeue_limit_total = 1000000\n")
- config_file.write("emergequeue_limit_diskonly = 1000000\n")
- config_file.write("emergequeue_limit_generate = 1000000\n")
-
- # Set display size
- config_file.write(f"screen_w = {self.display_size[0]}\n")
- config_file.write(f"screen_h = {self.display_size[1]}\n")
+ config = dict(
+ # Base config
+ mute_sound=True,
+ show_debug=False,
+ enable_client_modding=True,
+ csm_restriction_flags=0,
+ enable_mod_channels=True,
+ screen_w=self.display_size[0],
+ screen_h=self.display_size[1],
+ fov=self.fov_y,
  # Adapt HUD size to display size
- hud_scale = self.display_size[0] / Minetest.default_display_size[0]
- config_file.write(f"hud_scaling = {hud_scale}\n")
-
- # Set FOV
- config_file.write(f"fov = {self.fov_y}\n")
-
- # Seed the map generator
- if self.the_seed:
- config_file.write(f"fixed_map_seed = {self.the_seed}\n")
+ hud_scaling=self.display_size[0] / Minetest.default_display_size[0],
+ # Experimental settings to improve performance
+ server_map_save_interval=1000000,
+ profiler_print_interval=0,
+ active_block_range=2,
+ abm_time_budget=0.01,
+ abm_interval=0.1,
+ active_block_mgmt_interval=4.0,
+ server_unload_unused_data_timeout=1000000,
+ client_unload_unused_data_timeout=1000000,
+ full_block_send_enable_min_time_from_building=0.,
+ max_block_send_distance=100,
+ max_block_generate_distance=100,
+ num_emerge_threads=0,
+ emergequeue_limit_total=1000000,
+ emergequeue_limit_diskonly=1000000,
+ emergequeue_limit_generate=1000000,
+ )
 
- # Set from custom config dict
- # TODO enable overwriting of default settings
- for key, value in self.config_dict.items():
- config_file.write(f"{key} = {value}\n")
+ # Seed the map generator if not using a custom map
+ if self.world_seed:
+ config.update(fixed_map_seed=self.world_seed)
+ # Update config from existing config file
+ if os.path.exists(self.config_path):
+ config.update(read_config_file(self.config_path))
+ # Set from custom config dict
+ config.update(self.config_dict)
+ write_config_file(self.config_path, config)
 
- def seed(self, seed: int):
- self.the_seed = seed
+ def seed(self, seed: Optional[int] = None):
+ self._np_random = np.random.RandomState(seed or 0)
 
- def reset(self):
+ def reset(self, seed: Optional[int] = None, options: Optional[Dict[str, Any]] = None):
+ self.seed(seed=seed)
  if self.start_minetest:
  if self.reset_world:
  self._delete_world()
+ if self.reseed_on_reset:
+ self.world_seed = self._np_random.randint(np.iinfo(np.int64).max)
  self._enable_servermods()
  self._reset_minetest()
  self._reset_zmq()
@@ -382,7 +391,7 @@ def reset(self):
  obs, _, _, _, _ = unpack_pb_obs(byte_obs)
  self.last_obs = obs
  logging.debug("Received first obs: {}".format(obs.shape))
- return obs
+ return obs, {}
 
  def step(self, action: Dict[str, Any]):
  # Send action
@@ -407,10 +416,11 @@ def step(self, action: Dict[str, Any]):
 
  self.last_obs = next_obs
  logging.debug(f"Received obs - {next_obs.shape}; reward - {rew}; info - {info}")
- return next_obs, rew, done, info
+ return next_obs, rew, done, False, {"info": info}
 
  def render(self, render_mode: str = "human"):
  if render_mode == "human":
+ # TODO replace with pygame
  if self.render_img is None:
  # Setup figure
  plt.rcParams["toolbar"] = "None"

minetester/scripts/test_loop.py

@@ -4,7 +4,7 @@
 from minetester import Minetest
 
 env = Minetest(
- seed=42,
+ base_seed=42,
  start_minetest=True,
  sync_port=30010,
  sync_dtime=0.05,
@@ -15,12 +15,12 @@
 )
 
 render = True
-obs = env.reset()
+obs, _ = env.reset()
 done = False
 while not done:
  try:
  action = env.action_space.sample()
- obs, rew, done, info = env.step(action)
+ obs, rew, done, _, info = env.step(action)
  print(rew, done, info)
  if render:
  env.render()

minetester/scripts/test_loop_parallel.py

@@ -1,10 +1,10 @@
 import random
 from typing import Any, Dict, Optional
 
-from gym.wrappers import TimeLimit
+from gymnasium.wrappers import TimeLimit
+from gymnasium.vector import AsyncVectorEnv
 from minetester import Minetest
 from minetester.utils import start_xserver
-from stable_baselines3.common.vec_env import DummyVecEnv, SubprocVecEnv
 
 if __name__ == "__main__":
 
@@ -23,11 +23,12 @@ def _init():
  env = Minetest(
  env_port=5555 + rank,
  server_port=30000 + rank,
- seed=seed + rank,
+ base_seed=seed + rank,
  sync_port=30010 + rank,
  **env_kwargs,
  )
- env = TimeLimit(env, max_episode_steps=int(max_steps * random.random()))
+ # Assign random timelimit to check that resets work properly
+ env = TimeLimit(env, max_episode_steps=random.randint(max_steps // 2, max_steps))
  return env
 
  return _init
@@ -46,7 +47,7 @@ def _init():
 
  # Create a vectorized environment
  num_envs = 2 # Number of envs to use (<= number of avail. cpus)
- vec_env_cls = SubprocVecEnv # DummyVecEnv
+ vec_env_cls = AsyncVectorEnv
  venv = vec_env_cls(
  [
  make_env(rank=i, seed=seed, max_steps=max_steps, env_kwargs=env_kwargs)
@@ -59,15 +60,15 @@ def _init():
 
  # Start loop
  render = True
- obs = venv.reset()
+ obs, _ = venv.reset()
  done = [False] * num_envs
  step = 0
  while step < max_steps:
  print(f"Elapsed steps: {venv.get_attr('_elapsed_steps')}")
- actions = [venv.action_space.sample() for _ in range(num_envs)]
- obs, rew, done, info = venv.step(actions)
+ actions = venv.action_space.sample()
+ obs, rew, done, _, info = venv.step(actions)
  if render:
- venv.render()
+ venv.call("render")
  step += 1
  venv.close()
  xserver.terminate()

minetester/utils.py

@@ -176,3 +176,30 @@ def start_xserver(
  ]
  xserver_process = subprocess.Popen(cmd)
  return xserver_process
+
+
+def read_config_file(file_path):
+ config = {}
+ with open(file_path, 'r') as f:
+ for line in f:
+ line = line.strip()
+ if line and not line.startswith('#'):
+ key, value = line.split('=', 1)
+ key = key.strip()
+ value = value.strip()
+ if value.isdigit():
+ value = int(value)
+ elif value.replace('.', '', 1).isdigit():
+ value = float(value)
+ elif value.lower() == 'true':
+ value = True
+ elif value.lower() == 'false':
+ value = False
+ config[key] = value
+ return config
+
+
+def write_config_file(file_path, config):
+ with open(file_path, 'w') as f:
+ for key, value in config.items():
+ f.write(f'{key} = {value}\n')