INFO [6396] - 04/07/21 08:13:07 - 0:00:00 - ========== Running DOOM ========== INFO [6396] - 04/07/21 08:13:07 - 0:00:00 - Experiment will be saved in: ./dumped/default/phy2b4i0mx INFO [6396] - 04/07/21 08:13:07 - 0:00:00 - scenario: deathmatch map_ids_train: [1] map_ids_test: [1] freedoom: True height: 60 width: 108 gray: False use_screen_buffer: True use_depth_buffer: False labels_mapping: game_features: render_hud: False render_crosshair: True render_weapon: True hist_size: 4 frame_skip: 4 action_combinations: move_fb+turn_lr+move_lr+attack freelook: False speed: off crouch: off manual_control: False players_per_game: 1 player_rank: 0 dump_path: ./dumped/default/phy2b4i0mx visualize: False evaluate: 0 human_player: False reload: dump_freq: 0 gpu_id: 0 log_frequency: 100 network_type: dqn_ff use_bn: False batch_size: 32 replay_memory_size: 1000000 start_decay: 0 stop_decay: 1000000 final_decay: 0.1 gamma: 0.99 dueling_network: False recurrence: clip_delta: 1.0 variable_dim: [32, 32] bucket_size: [1, 1] hidden_dim: 512 update_frequency: 4 dropout: 0.0 optimizer: rmsprop,lr=0.0002 wad: n_bots: 8 reward_values: randomize_textures: False init_bots_health: 100 game_variables: [('health', 101), ('sel_ammo', 301)] n_variables: 2 n_features: 0 n_fm: 3 use_continuous: False episode_time: None eval_freq: 20000 eval_time: 900 Traceback (most recent call last): File "arnold.py", line 24, in parse_game_args(remaining + ['--dump_path', dump_path]) File "/kaggle/working/Arnold/src/args.py", line 114, in parse_game_args module.main(parser, args) File "/kaggle/working/Arnold/src/doom/scenarios/deathmatch.py", line 80, in main torch.cuda.set_device(params.gpu_id) File "/opt/conda/lib/python3.7/site-packages/torch/cuda/__init__.py", line 263, in set_device torch._C._cuda_setDevice(device) AttributeError: module 'torch._C' has no attribute '_cuda_setDevice' bash: line 4: --freedoom: command not found bash: line 5: --height: command not found bash: line 6: --width: command not found bash: line 7: --gray: command not found bash: line 8: --use_screen_buffer: command not found bash: line 9: --use_depth_buffer: command not found bash: line 10: --labels_mapping: command not found bash: line 11: --game_features: command not found bash: line 12: --render_hud: command not found bash: line 13: --render_crosshair: command not found bash: line 14: --render_weapon: command not found bash: line 15: --hist_size: command not found bash: line 16: --frame_skip: command not found bash: line 19: --action_combinations: command not found bash: line 20: --freelook: command not found bash: line 21: --speed: command not found bash: line 22: --crouch: command not found bash: line 25: --batch_size: command not found bash: line 26: --replay_memory_size: command not found bash: line 27: --start_decay: command not found bash: line 28: --stop_decay: command not found bash: line 29: --final_decay: command not found bash: line 30: gamma: command not found bash: line 31: --dueling_network: command not found bash: line 32: --clip_delta: command not found bash: line 33: --update_frequency: command not found bash: line 34: --dropout: command not found bash: line 35: --optimizer: command not found bash: line 38: --network_type: command not found bash: line 39: --recurrence: command not found bash: line 40: --n_rec_layers: command not found bash: line 41: --n_rec_updates: command not found bash: line 42: --remember: command not found bash: line 43: --use_bn: command not found bash: line 44: --variable_dim: command not found bash: line 45: --bucket_size: command not found bash: line 46: --hidden_dim: command not found bash: line 49: --scenario: command not found bash: line 50: --wad: command not found bash: line 51: --map_ids_train: command not found bash: line 52: --map_ids_test: command not found bash: line 53: --n_bots: command not found bash: line 54: --randomize_textures: command not found bash: line 55: --init_bots_health: command not found bash: line 58: --exp_name: command not found bash: line 59: --dump_freq: command not found bash: line 60: --gpu_id: command not found --------------------------------------------------------------------------- CalledProcessError Traceback (most recent call last) in ----> 1 get_ipython().run_cell_magic('bash', '', 'python arnold.py\n\n## General parameters about the game\n--freedoom "true" # use freedoom resources\n--height 60 # screen height\n--width 108 # screen width\n--gray "false" # use grayscale screen\n--use_screen_buffer "true" # use the screen buffer (what the player sees)\n--use_depth_buffer "false" # use the depth buffer\n--labels_mapping "" # use extra feature maps for specific objects\n--game_features "target,enemy" # game features prediction (auxiliary tasks)\n--render_hud "false" # render the HUD (status bar in the bottom of the screen)\n--render_crosshair "true" # render crosshair (targeting aid in the center of the screen)\n--render_weapon "true" # render weapon\n--hist_size 4 # history size\n--frame_skip 4 # frame skip (1 = keep every frame)\n\n## Agent allowed actions\n--action_combinations "attack+move_lr;turn_lr;move_fb" # agent allowed actions\n--freelook "false" # allow the agent to look up and down\n--speed "on" # make the agent run\n--crouch "off" # make the agent crouch\n\n## Training parameters\n--batch_size 32 # batch size\n--replay_memory_size 1000000 # maximum number of frames in the replay memory\n--start_decay 0 # epsilon decay iteration start\n--stop_decay 1000000 # epsilon decay iteration end\n--final_decay 0.1 # final epsilon value\ngamma 0.99 # discount factor gamma\n--dueling_network "false" # use a dueling architecture\n--clip_delta 1.0 # clip the delta loss\n--update_frequency 4 # DQN update frequency\n--dropout 0.5 # dropout on CNN output layer\n--optimizer "rmsprop,lr=0.0002" # network optimizer\n\n## Network architecture\n--network_type "dqn_rnn" # network type (dqn_ff / dqn_rnn)\n--recurrence "lstm" # recurrent network type (rnn / gru / lstm)\n--n_rec_layers 1 # number of layers in the recurrent network\n--n_rec_updates 5 # number of updates by sample\n--remember 1 # remember all frames during evaluation\n--use_bn "off" # use BatchNorm when processing the screen\n--variable_dim "32" # game variables embeddings dimension\n--bucket_size "[10, 1]" # bucket game variables (typically health / ammo)\n--hidden_dim 512 # hidden layers dimension\n\n## Scenario parameters (these parameters will differ based on the scenario)\n--scenario "deathmatch" # scenario\n--wad "full_deathmatch" # WAD file (scenario file)\n--map_ids_train "2,3,4,5" # maps to train the model\n--map_ids_test "6,7,8" # maps to test the model\n--n_bots 8 # number of enemy bots\n--randomize_textures "true" # randomize walls / floors / ceils textures during training\n--init_bots_health 20 # reduce initial life of enemy bots (helps a lot when using pistol)\n\n## Various\n--exp_name new_train # experiment name\n--dump_freq 200000 # periodically dump the model\n--gpu_id -1 # GPU ID (-1 to run on CPU)\n') /opt/conda/lib/python3.7/site-packages/IPython/core/interactiveshell.py in run_cell_magic(self, magic_name, line, cell) 2389 with self.builtin_trap: 2390 args = (magic_arg_s, cell) -> 2391 result = fn(*args, **kwargs) 2392 return result 2393 /opt/conda/lib/python3.7/site-packages/IPython/core/magics/script.py in named_script_magic(line, cell) 140 else: 141 line = script --> 142 return self.shebang(line, cell) 143 144 # write a basic docstring: in shebang(self, line, cell) /opt/conda/lib/python3.7/site-packages/IPython/core/magic.py in (f, *a, **k) 185 # but it's overkill for just that one bit of state. 186 def magic_deco(arg): --> 187 call = lambda f, *a, **k: f(*a, **k) 188 189 if callable(arg): /opt/conda/lib/python3.7/site-packages/IPython/core/magics/script.py in shebang(self, line, cell) 243 sys.stderr.flush() 244 if args.raise_error and p.returncode!=0: --> 245 raise CalledProcessError(p.returncode, cell, output=out, stderr=err) 246 247 def _run_script(self, p, cell, to_close): CalledProcessError: Command 'b'python arnold.py\n\n## General parameters about the game\n--freedoom "true" # use freedoom resources\n--height 60 # screen height\n--width 108 # screen width\n--gray "false" # use grayscale screen\n--use_screen_buffer "true" # use the screen buffer (what the player sees)\n--use_depth_buffer "false" # use the depth buffer\n--labels_mapping "" # use extra feature maps for specific objects\n--game_features "target,enemy" # game features prediction (auxiliary tasks)\n--render_hud "false" # render the HUD (status bar in the bottom of the screen)\n--render_crosshair "true" # render crosshair (targeting aid in the center of the screen)\n--render_weapon "true" # render weapon\n--hist_size 4 # history size\n--frame_skip 4 # frame skip (1 = keep every frame)\n\n## Agent allowed actions\n--action_combinations "attack+move_lr;turn_lr;move_fb" # agent allowed actions\n--freelook "false" # allow the agent to look up and down\n--speed "on" # make the agent run\n--crouch "off" # make the agent crouch\n\n## Training parameters\n--batch_size 32 # batch size\n--replay_memory_size 1000000 # maximum number of frames in the replay memory\n--start_decay 0 # epsilon decay iteration start\n--stop_decay 1000000 # epsilon decay iteration end\n--final_decay 0.1 # final epsilon value\ngamma 0.99 # discount factor gamma\n--dueling_network "false" # use a dueling architecture\n--clip_delta 1.0 # clip the delta loss\n--update_frequency 4 # DQN update frequency\n--dropout 0.5 # dropout on CNN output layer\n--optimizer "rmsprop,lr=0.0002" # network optimizer\n\n## Network architecture\n--network_type "dqn_rnn" # network type (dqn_ff / dqn_rnn)\n--recurrence "lstm" # recurrent network type (rnn / gru / lstm)\n--n_rec_layers 1 # number of layers in the recurrent network\n--n_rec_updates 5 # number of updates by sample\n--remember 1 # remember all frames during evaluation\n--use_bn "off" # use BatchNorm when processing the screen\n--variable_dim "32" # game variables embeddings dimension\n--bucket_size "[10, 1]" # bucket game variables (typically health / ammo)\n--hidden_dim 512 # hidden layers dimension\n\n## Scenario parameters (these parameters will differ based on the scenario)\n--scenario "deathmatch" # scenario\n--wad "full_deathmatch" # WAD file (scenario file)\n--map_ids_train "2,3,4,5" # maps to train the model\n--map_ids_test "6,7,8" # maps to test the model\n--n_bots 8 # number of enemy bots\n--randomize_textures "true" # randomize walls / floors / ceils textures during training\n--init_bots_health 20 # reduce initial life of enemy bots (helps a lot when using pistol)\n\n## Various\n--exp_name new_train # experiment name\n--dump_freq 200000 # periodically dump the model\n--gpu_id -1 # GPU ID (-1 to run on CPU)\n'' returned non-zero exit status 127.