bensalem14 commited on
Commit
a66185d
·
verified ·
1 Parent(s): 0e4b00e

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. replay.mp4 +2 -2
  3. sf_log.txt +346 -0
README.md CHANGED
@@ -15,7 +15,7 @@ model-index:
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
- value: 6.53 +/- 4.98
19
  name: mean_reward
20
  verified: false
21
  ---
 
15
  type: doom_health_gathering_supreme
16
  metrics:
17
  - type: mean_reward
18
+ value: 5.45 +/- 2.06
19
  name: mean_reward
20
  verified: false
21
  ---
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af88d990610b43da6ddc2408bc09c8a0c75ff3eb42161ebf512205a266218535
3
- size 11428623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22399c78752a4336b32cf443cdf79c73eaf0cbd8853c67abb8655745c9e19923
3
+ size 9643677
sf_log.txt CHANGED
@@ -1924,3 +1924,349 @@ main_loop: 44.4594
1924
  [2025-08-23 02:17:12,809][13958] Avg episode rewards: #0: 11.834, true rewards: #0: 6.534
1925
  [2025-08-23 02:17:12,810][13958] Avg episode reward: 11.834, avg true_objective: 6.534
1926
  [2025-08-23 02:17:48,823][13958] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1924
  [2025-08-23 02:17:12,809][13958] Avg episode rewards: #0: 11.834, true rewards: #0: 6.534
1925
  [2025-08-23 02:17:12,810][13958] Avg episode reward: 11.834, avg true_objective: 6.534
1926
  [2025-08-23 02:17:48,823][13958] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
1927
+ [2025-08-23 02:18:00,663][13958] The model has been pushed to https://huggingface.co/bensalem14/rl_course_vizdoom_health_gathering_supreme
1928
+ [2025-08-23 02:19:05,470][13958] Loading legacy config file train_dir/doom_health_gathering_supreme_2222/cfg.json instead of train_dir/doom_health_gathering_supreme_2222/config.json
1929
+ [2025-08-23 02:19:05,472][13958] Loading existing experiment configuration from train_dir/doom_health_gathering_supreme_2222/config.json
1930
+ [2025-08-23 02:19:05,473][13958] Overriding arg 'experiment' with value 'doom_health_gathering_supreme_2222' passed from command line
1931
+ [2025-08-23 02:19:05,474][13958] Overriding arg 'train_dir' with value 'train_dir' passed from command line
1932
+ [2025-08-23 02:19:05,475][13958] Overriding arg 'num_workers' with value 1 passed from command line
1933
+ [2025-08-23 02:19:05,475][13958] Adding new argument 'lr_adaptive_min'=1e-06 that is not in the saved config file!
1934
+ [2025-08-23 02:19:05,476][13958] Adding new argument 'lr_adaptive_max'=0.01 that is not in the saved config file!
1935
+ [2025-08-23 02:19:05,477][13958] Adding new argument 'env_gpu_observations'=True that is not in the saved config file!
1936
+ [2025-08-23 02:19:05,478][13958] Adding new argument 'no_render'=True that is not in the saved config file!
1937
+ [2025-08-23 02:19:05,479][13958] Adding new argument 'save_video'=True that is not in the saved config file!
1938
+ [2025-08-23 02:19:05,479][13958] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
1939
+ [2025-08-23 02:19:05,480][13958] Adding new argument 'video_name'=None that is not in the saved config file!
1940
+ [2025-08-23 02:19:05,481][13958] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
1941
+ [2025-08-23 02:19:05,482][13958] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
1942
+ [2025-08-23 02:19:05,482][13958] Adding new argument 'push_to_hub'=False that is not in the saved config file!
1943
+ [2025-08-23 02:19:05,483][13958] Adding new argument 'hf_repository'=None that is not in the saved config file!
1944
+ [2025-08-23 02:19:05,484][13958] Adding new argument 'policy_index'=0 that is not in the saved config file!
1945
+ [2025-08-23 02:19:05,485][13958] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
1946
+ [2025-08-23 02:19:05,485][13958] Adding new argument 'train_script'=None that is not in the saved config file!
1947
+ [2025-08-23 02:19:05,486][13958] Adding new argument 'enjoy_script'=None that is not in the saved config file!
1948
+ [2025-08-23 02:19:05,487][13958] Using frameskip 1 and render_action_repeat=4 for evaluation
1949
+ [2025-08-23 02:19:05,513][13958] RunningMeanStd input shape: (3, 72, 128)
1950
+ [2025-08-23 02:19:05,515][13958] RunningMeanStd input shape: (1,)
1951
+ [2025-08-23 02:19:05,524][13958] ConvEncoder: input_channels=3
1952
+ [2025-08-23 02:19:05,562][13958] Conv encoder output size: 512
1953
+ [2025-08-23 02:19:05,563][13958] Policy head output size: 512
1954
+ [2025-08-23 02:19:05,583][13958] Loading state from checkpoint train_dir/doom_health_gathering_supreme_2222/checkpoint_p0/checkpoint_000539850_4422451200.pth...
1955
+ [2025-08-23 02:19:06,001][13958] Num frames 100...
1956
+ [2025-08-23 02:19:06,130][13958] Num frames 200...
1957
+ [2025-08-23 02:19:06,246][13958] Num frames 300...
1958
+ [2025-08-23 02:19:06,367][13958] Num frames 400...
1959
+ [2025-08-23 02:19:06,486][13958] Num frames 500...
1960
+ [2025-08-23 02:19:06,605][13958] Num frames 600...
1961
+ [2025-08-23 02:19:06,726][13958] Num frames 700...
1962
+ [2025-08-23 02:19:06,844][13958] Num frames 800...
1963
+ [2025-08-23 02:19:07,016][13958] Num frames 900...
1964
+ [2025-08-23 02:19:07,196][13958] Num frames 1000...
1965
+ [2025-08-23 02:19:07,369][13958] Num frames 1100...
1966
+ [2025-08-23 02:19:07,540][13958] Num frames 1200...
1967
+ [2025-08-23 02:19:07,660][13958] Avg episode rewards: #0: 38.360, true rewards: #0: 12.360
1968
+ [2025-08-23 02:19:07,661][13958] Avg episode reward: 38.360, avg true_objective: 12.360
1969
+ [2025-08-23 02:19:07,773][13958] Num frames 1300...
1970
+ [2025-08-23 02:19:07,942][13958] Num frames 1400...
1971
+ [2025-08-23 02:19:08,109][13958] Num frames 1500...
1972
+ [2025-08-23 02:19:08,285][13958] Num frames 1600...
1973
+ [2025-08-23 02:19:08,466][13958] Num frames 1700...
1974
+ [2025-08-23 02:19:08,641][13958] Num frames 1800...
1975
+ [2025-08-23 02:19:08,822][13958] Num frames 1900...
1976
+ [2025-08-23 02:19:09,007][13958] Num frames 2000...
1977
+ [2025-08-23 02:19:09,155][13958] Num frames 2100...
1978
+ [2025-08-23 02:19:09,287][13958] Num frames 2200...
1979
+ [2025-08-23 02:19:09,409][13958] Num frames 2300...
1980
+ [2025-08-23 02:19:09,530][13958] Num frames 2400...
1981
+ [2025-08-23 02:19:09,654][13958] Num frames 2500...
1982
+ [2025-08-23 02:19:09,776][13958] Num frames 2600...
1983
+ [2025-08-23 02:19:09,909][13958] Num frames 2700...
1984
+ [2025-08-23 02:19:10,036][13958] Num frames 2800...
1985
+ [2025-08-23 02:19:10,160][13958] Num frames 2900...
1986
+ [2025-08-23 02:19:10,302][13958] Num frames 3000...
1987
+ [2025-08-23 02:19:10,430][13958] Num frames 3100...
1988
+ [2025-08-23 02:19:10,555][13958] Num frames 3200...
1989
+ [2025-08-23 02:19:10,681][13958] Num frames 3300...
1990
+ [2025-08-23 02:19:10,781][13958] Avg episode rewards: #0: 53.679, true rewards: #0: 16.680
1991
+ [2025-08-23 02:19:10,782][13958] Avg episode reward: 53.679, avg true_objective: 16.680
1992
+ [2025-08-23 02:19:10,862][13958] Num frames 3400...
1993
+ [2025-08-23 02:19:10,988][13958] Num frames 3500...
1994
+ [2025-08-23 02:19:11,115][13958] Num frames 3600...
1995
+ [2025-08-23 02:19:11,238][13958] Num frames 3700...
1996
+ [2025-08-23 02:19:11,371][13958] Num frames 3800...
1997
+ [2025-08-23 02:19:11,491][13958] Num frames 3900...
1998
+ [2025-08-23 02:19:11,642][13958] Num frames 4000...
1999
+ [2025-08-23 02:19:11,764][13958] Num frames 4100...
2000
+ [2025-08-23 02:19:11,887][13958] Num frames 4200...
2001
+ [2025-08-23 02:19:12,012][13958] Num frames 4300...
2002
+ [2025-08-23 02:19:12,139][13958] Num frames 4400...
2003
+ [2025-08-23 02:19:12,265][13958] Num frames 4500...
2004
+ [2025-08-23 02:19:12,399][13958] Num frames 4600...
2005
+ [2025-08-23 02:19:12,524][13958] Num frames 4700...
2006
+ [2025-08-23 02:19:12,650][13958] Num frames 4800...
2007
+ [2025-08-23 02:19:12,776][13958] Num frames 4900...
2008
+ [2025-08-23 02:19:12,901][13958] Num frames 5000...
2009
+ [2025-08-23 02:19:13,028][13958] Num frames 5100...
2010
+ [2025-08-23 02:19:13,164][13958] Num frames 5200...
2011
+ [2025-08-23 02:19:13,290][13958] Num frames 5300...
2012
+ [2025-08-23 02:19:13,426][13958] Num frames 5400...
2013
+ [2025-08-23 02:19:13,527][13958] Avg episode rewards: #0: 57.119, true rewards: #0: 18.120
2014
+ [2025-08-23 02:19:13,528][13958] Avg episode reward: 57.119, avg true_objective: 18.120
2015
+ [2025-08-23 02:19:13,608][13958] Num frames 5500...
2016
+ [2025-08-23 02:19:13,736][13958] Num frames 5600...
2017
+ [2025-08-23 02:19:13,860][13958] Num frames 5700...
2018
+ [2025-08-23 02:19:13,982][13958] Num frames 5800...
2019
+ [2025-08-23 02:19:14,107][13958] Num frames 5900...
2020
+ [2025-08-23 02:19:14,228][13958] Num frames 6000...
2021
+ [2025-08-23 02:19:14,349][13958] Num frames 6100...
2022
+ [2025-08-23 02:19:14,481][13958] Num frames 6200...
2023
+ [2025-08-23 02:19:14,603][13958] Num frames 6300...
2024
+ [2025-08-23 02:19:14,731][13958] Num frames 6400...
2025
+ [2025-08-23 02:19:14,856][13958] Num frames 6500...
2026
+ [2025-08-23 02:19:14,981][13958] Num frames 6600...
2027
+ [2025-08-23 02:19:15,106][13958] Num frames 6700...
2028
+ [2025-08-23 02:19:15,231][13958] Num frames 6800...
2029
+ [2025-08-23 02:19:15,358][13958] Num frames 6900...
2030
+ [2025-08-23 02:19:15,492][13958] Num frames 7000...
2031
+ [2025-08-23 02:19:15,620][13958] Num frames 7100...
2032
+ [2025-08-23 02:19:15,746][13958] Num frames 7200...
2033
+ [2025-08-23 02:19:15,871][13958] Num frames 7300...
2034
+ [2025-08-23 02:19:15,997][13958] Num frames 7400...
2035
+ [2025-08-23 02:19:16,126][13958] Num frames 7500...
2036
+ [2025-08-23 02:19:16,224][13958] Avg episode rewards: #0: 59.589, true rewards: #0: 18.840
2037
+ [2025-08-23 02:19:16,225][13958] Avg episode reward: 59.589, avg true_objective: 18.840
2038
+ [2025-08-23 02:19:16,305][13958] Num frames 7600...
2039
+ [2025-08-23 02:19:16,430][13958] Num frames 7700...
2040
+ [2025-08-23 02:19:16,570][13958] Num frames 7800...
2041
+ [2025-08-23 02:19:16,701][13958] Num frames 7900...
2042
+ [2025-08-23 02:19:16,826][13958] Num frames 8000...
2043
+ [2025-08-23 02:19:16,953][13958] Num frames 8100...
2044
+ [2025-08-23 02:19:17,079][13958] Num frames 8200...
2045
+ [2025-08-23 02:19:17,203][13958] Num frames 8300...
2046
+ [2025-08-23 02:19:17,328][13958] Num frames 8400...
2047
+ [2025-08-23 02:19:17,453][13958] Num frames 8500...
2048
+ [2025-08-23 02:19:17,589][13958] Num frames 8600...
2049
+ [2025-08-23 02:19:17,713][13958] Num frames 8700...
2050
+ [2025-08-23 02:19:17,838][13958] Num frames 8800...
2051
+ [2025-08-23 02:19:17,966][13958] Num frames 8900...
2052
+ [2025-08-23 02:19:18,090][13958] Num frames 9000...
2053
+ [2025-08-23 02:19:18,215][13958] Num frames 9100...
2054
+ [2025-08-23 02:19:18,343][13958] Num frames 9200...
2055
+ [2025-08-23 02:19:18,470][13958] Num frames 9300...
2056
+ [2025-08-23 02:19:18,606][13958] Num frames 9400...
2057
+ [2025-08-23 02:19:18,732][13958] Num frames 9500...
2058
+ [2025-08-23 02:19:18,857][13958] Num frames 9600...
2059
+ [2025-08-23 02:19:18,957][13958] Avg episode rewards: #0: 60.871, true rewards: #0: 19.272
2060
+ [2025-08-23 02:19:18,959][13958] Avg episode reward: 60.871, avg true_objective: 19.272
2061
+ [2025-08-23 02:19:19,040][13958] Num frames 9700...
2062
+ [2025-08-23 02:19:19,206][13958] Num frames 9800...
2063
+ [2025-08-23 02:19:19,382][13958] Num frames 9900...
2064
+ [2025-08-23 02:19:19,558][13958] Num frames 10000...
2065
+ [2025-08-23 02:19:19,736][13958] Num frames 10100...
2066
+ [2025-08-23 02:19:19,909][13958] Num frames 10200...
2067
+ [2025-08-23 02:19:20,086][13958] Num frames 10300...
2068
+ [2025-08-23 02:19:20,256][13958] Num frames 10400...
2069
+ [2025-08-23 02:19:20,429][13958] Num frames 10500...
2070
+ [2025-08-23 02:19:20,605][13958] Num frames 10600...
2071
+ [2025-08-23 02:19:20,801][13958] Num frames 10700...
2072
+ [2025-08-23 02:19:20,985][13958] Num frames 10800...
2073
+ [2025-08-23 02:19:21,169][13958] Num frames 10900...
2074
+ [2025-08-23 02:19:21,335][13958] Num frames 11000...
2075
+ [2025-08-23 02:19:21,466][13958] Num frames 11100...
2076
+ [2025-08-23 02:19:21,591][13958] Num frames 11200...
2077
+ [2025-08-23 02:19:21,729][13958] Num frames 11300...
2078
+ [2025-08-23 02:19:21,856][13958] Num frames 11400...
2079
+ [2025-08-23 02:19:21,989][13958] Num frames 11500...
2080
+ [2025-08-23 02:19:22,116][13958] Num frames 11600...
2081
+ [2025-08-23 02:19:22,247][13958] Num frames 11700...
2082
+ [2025-08-23 02:19:22,347][13958] Avg episode rewards: #0: 61.559, true rewards: #0: 19.560
2083
+ [2025-08-23 02:19:22,347][13958] Avg episode reward: 61.559, avg true_objective: 19.560
2084
+ [2025-08-23 02:19:22,428][13958] Num frames 11800...
2085
+ [2025-08-23 02:19:22,565][13958] Num frames 11900...
2086
+ [2025-08-23 02:19:22,697][13958] Num frames 12000...
2087
+ [2025-08-23 02:19:22,833][13958] Num frames 12100...
2088
+ [2025-08-23 02:19:22,957][13958] Num frames 12200...
2089
+ [2025-08-23 02:19:23,080][13958] Num frames 12300...
2090
+ [2025-08-23 02:19:23,204][13958] Num frames 12400...
2091
+ [2025-08-23 02:19:23,333][13958] Num frames 12500...
2092
+ [2025-08-23 02:19:23,469][13958] Num frames 12600...
2093
+ [2025-08-23 02:19:23,595][13958] Num frames 12700...
2094
+ [2025-08-23 02:19:23,719][13958] Num frames 12800...
2095
+ [2025-08-23 02:19:23,856][13958] Num frames 12900...
2096
+ [2025-08-23 02:19:23,983][13958] Num frames 13000...
2097
+ [2025-08-23 02:19:24,109][13958] Num frames 13100...
2098
+ [2025-08-23 02:19:24,235][13958] Num frames 13200...
2099
+ [2025-08-23 02:19:24,359][13958] Num frames 13300...
2100
+ [2025-08-23 02:19:24,482][13958] Num frames 13400...
2101
+ [2025-08-23 02:19:24,609][13958] Num frames 13500...
2102
+ [2025-08-23 02:19:24,737][13958] Num frames 13600...
2103
+ [2025-08-23 02:19:24,873][13958] Num frames 13700...
2104
+ [2025-08-23 02:19:25,001][13958] Num frames 13800...
2105
+ [2025-08-23 02:19:25,105][13958] Avg episode rewards: #0: 62.193, true rewards: #0: 19.766
2106
+ [2025-08-23 02:19:25,105][13958] Avg episode reward: 62.193, avg true_objective: 19.766
2107
+ [2025-08-23 02:19:25,186][13958] Num frames 13900...
2108
+ [2025-08-23 02:19:25,311][13958] Num frames 14000...
2109
+ [2025-08-23 02:19:25,436][13958] Num frames 14100...
2110
+ [2025-08-23 02:19:25,562][13958] Num frames 14200...
2111
+ [2025-08-23 02:19:25,687][13958] Num frames 14300...
2112
+ [2025-08-23 02:19:25,823][13958] Num frames 14400...
2113
+ [2025-08-23 02:19:25,949][13958] Num frames 14500...
2114
+ [2025-08-23 02:19:26,074][13958] Num frames 14600...
2115
+ [2025-08-23 02:19:26,198][13958] Num frames 14700...
2116
+ [2025-08-23 02:19:26,327][13958] Num frames 14800...
2117
+ [2025-08-23 02:19:26,455][13958] Num frames 14900...
2118
+ [2025-08-23 02:19:26,586][13958] Num frames 15000...
2119
+ [2025-08-23 02:19:26,715][13958] Num frames 15100...
2120
+ [2025-08-23 02:19:26,850][13958] Num frames 15200...
2121
+ [2025-08-23 02:19:26,983][13958] Num frames 15300...
2122
+ [2025-08-23 02:19:27,110][13958] Num frames 15400...
2123
+ [2025-08-23 02:19:27,237][13958] Num frames 15500...
2124
+ [2025-08-23 02:19:27,365][13958] Num frames 15600...
2125
+ [2025-08-23 02:19:27,488][13958] Num frames 15700...
2126
+ [2025-08-23 02:19:27,612][13958] Num frames 15800...
2127
+ [2025-08-23 02:19:27,740][13958] Num frames 15900...
2128
+ [2025-08-23 02:19:27,841][13958] Avg episode rewards: #0: 61.794, true rewards: #0: 19.920
2129
+ [2025-08-23 02:19:27,842][13958] Avg episode reward: 61.794, avg true_objective: 19.920
2130
+ [2025-08-23 02:19:27,933][13958] Num frames 16000...
2131
+ [2025-08-23 02:19:28,058][13958] Num frames 16100...
2132
+ [2025-08-23 02:19:28,184][13958] Num frames 16200...
2133
+ [2025-08-23 02:19:28,307][13958] Num frames 16300...
2134
+ [2025-08-23 02:19:28,431][13958] Num frames 16400...
2135
+ [2025-08-23 02:19:28,557][13958] Num frames 16500...
2136
+ [2025-08-23 02:19:28,683][13958] Num frames 16600...
2137
+ [2025-08-23 02:19:28,809][13958] Num frames 16700...
2138
+ [2025-08-23 02:19:28,944][13958] Num frames 16800...
2139
+ [2025-08-23 02:19:29,070][13958] Num frames 16900...
2140
+ [2025-08-23 02:19:29,192][13958] Num frames 17000...
2141
+ [2025-08-23 02:19:29,319][13958] Num frames 17100...
2142
+ [2025-08-23 02:19:29,444][13958] Num frames 17200...
2143
+ [2025-08-23 02:19:29,568][13958] Num frames 17300...
2144
+ [2025-08-23 02:19:29,694][13958] Num frames 17400...
2145
+ [2025-08-23 02:19:29,820][13958] Num frames 17500...
2146
+ [2025-08-23 02:19:29,955][13958] Num frames 17600...
2147
+ [2025-08-23 02:19:30,083][13958] Num frames 17700...
2148
+ [2025-08-23 02:19:30,207][13958] Num frames 17800...
2149
+ [2025-08-23 02:19:30,337][13958] Num frames 17900...
2150
+ [2025-08-23 02:19:30,460][13958] Num frames 18000...
2151
+ [2025-08-23 02:19:30,560][13958] Avg episode rewards: #0: 61.817, true rewards: #0: 20.040
2152
+ [2025-08-23 02:19:30,561][13958] Avg episode reward: 61.817, avg true_objective: 20.040
2153
+ [2025-08-23 02:19:30,641][13958] Num frames 18100...
2154
+ [2025-08-23 02:19:30,765][13958] Num frames 18200...
2155
+ [2025-08-23 02:19:30,892][13958] Num frames 18300...
2156
+ [2025-08-23 02:19:31,030][13958] Num frames 18400...
2157
+ [2025-08-23 02:19:31,155][13958] Num frames 18500...
2158
+ [2025-08-23 02:19:31,282][13958] Num frames 18600...
2159
+ [2025-08-23 02:19:31,459][13958] Num frames 18700...
2160
+ [2025-08-23 02:19:31,638][13958] Num frames 18800...
2161
+ [2025-08-23 02:19:31,814][13958] Num frames 18900...
2162
+ [2025-08-23 02:19:31,989][13958] Num frames 19000...
2163
+ [2025-08-23 02:19:32,180][13958] Num frames 19100...
2164
+ [2025-08-23 02:19:32,353][13958] Num frames 19200...
2165
+ [2025-08-23 02:19:32,525][13958] Num frames 19300...
2166
+ [2025-08-23 02:19:32,702][13958] Num frames 19400...
2167
+ [2025-08-23 02:19:32,886][13958] Num frames 19500...
2168
+ [2025-08-23 02:19:33,063][13958] Num frames 19600...
2169
+ [2025-08-23 02:19:33,249][13958] Num frames 19700...
2170
+ [2025-08-23 02:19:33,431][13958] Num frames 19800...
2171
+ [2025-08-23 02:19:33,581][13958] Num frames 19900...
2172
+ [2025-08-23 02:19:33,707][13958] Num frames 20000...
2173
+ [2025-08-23 02:19:33,845][13958] Num frames 20100...
2174
+ [2025-08-23 02:19:33,944][13958] Avg episode rewards: #0: 62.335, true rewards: #0: 20.136
2175
+ [2025-08-23 02:19:33,945][13958] Avg episode reward: 62.335, avg true_objective: 20.136
2176
+ [2025-08-23 02:21:30,154][13958] Replay video saved to train_dir/doom_health_gathering_supreme_2222/replay.mp4!
2177
+ [2025-08-23 02:22:38,807][13958] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
2178
+ [2025-08-23 02:22:38,808][13958] Overriding arg 'num_workers' with value 1 passed from command line
2179
+ [2025-08-23 02:22:38,809][13958] Adding new argument 'no_render'=True that is not in the saved config file!
2180
+ [2025-08-23 02:22:38,810][13958] Adding new argument 'save_video'=True that is not in the saved config file!
2181
+ [2025-08-23 02:22:38,811][13958] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
2182
+ [2025-08-23 02:22:38,812][13958] Adding new argument 'video_name'=None that is not in the saved config file!
2183
+ [2025-08-23 02:22:38,813][13958] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
2184
+ [2025-08-23 02:22:38,814][13958] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
2185
+ [2025-08-23 02:22:38,815][13958] Adding new argument 'push_to_hub'=True that is not in the saved config file!
2186
+ [2025-08-23 02:22:38,816][13958] Adding new argument 'hf_repository'='bensalem14/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
2187
+ [2025-08-23 02:22:38,817][13958] Adding new argument 'policy_index'=0 that is not in the saved config file!
2188
+ [2025-08-23 02:22:38,818][13958] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
2189
+ [2025-08-23 02:22:38,819][13958] Adding new argument 'train_script'=None that is not in the saved config file!
2190
+ [2025-08-23 02:22:38,819][13958] Adding new argument 'enjoy_script'=None that is not in the saved config file!
2191
+ [2025-08-23 02:22:38,820][13958] Using frameskip 1 and render_action_repeat=4 for evaluation
2192
+ [2025-08-23 02:22:38,844][13958] RunningMeanStd input shape: (3, 72, 128)
2193
+ [2025-08-23 02:22:38,845][13958] RunningMeanStd input shape: (1,)
2194
+ [2025-08-23 02:22:38,855][13958] ConvEncoder: input_channels=3
2195
+ [2025-08-23 02:22:38,885][13958] Conv encoder output size: 512
2196
+ [2025-08-23 02:22:38,886][13958] Policy head output size: 512
2197
+ [2025-08-23 02:22:38,902][13958] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000982_4022272.pth...
2198
+ [2025-08-23 02:22:39,336][13958] Num frames 100...
2199
+ [2025-08-23 02:22:39,456][13958] Num frames 200...
2200
+ [2025-08-23 02:22:39,575][13958] Num frames 300...
2201
+ [2025-08-23 02:22:39,696][13958] Num frames 400...
2202
+ [2025-08-23 02:22:39,820][13958] Num frames 500...
2203
+ [2025-08-23 02:22:39,939][13958] Num frames 600...
2204
+ [2025-08-23 02:22:40,013][13958] Avg episode rewards: #0: 12.160, true rewards: #0: 6.160
2205
+ [2025-08-23 02:22:40,014][13958] Avg episode reward: 12.160, avg true_objective: 6.160
2206
+ [2025-08-23 02:22:40,117][13958] Num frames 700...
2207
+ [2025-08-23 02:22:40,238][13958] Num frames 800...
2208
+ [2025-08-23 02:22:40,380][13958] Avg episode rewards: #0: 7.360, true rewards: #0: 4.360
2209
+ [2025-08-23 02:22:40,381][13958] Avg episode reward: 7.360, avg true_objective: 4.360
2210
+ [2025-08-23 02:22:40,415][13958] Num frames 900...
2211
+ [2025-08-23 02:22:40,533][13958] Num frames 1000...
2212
+ [2025-08-23 02:22:40,654][13958] Num frames 1100...
2213
+ [2025-08-23 02:22:40,773][13958] Num frames 1200...
2214
+ [2025-08-23 02:22:40,931][13958] Avg episode rewards: #0: 6.960, true rewards: #0: 4.293
2215
+ [2025-08-23 02:22:40,932][13958] Avg episode reward: 6.960, avg true_objective: 4.293
2216
+ [2025-08-23 02:22:40,949][13958] Num frames 1300...
2217
+ [2025-08-23 02:22:41,077][13958] Num frames 1400...
2218
+ [2025-08-23 02:22:41,196][13958] Num frames 1500...
2219
+ [2025-08-23 02:22:41,317][13958] Num frames 1600...
2220
+ [2025-08-23 02:22:41,436][13958] Num frames 1700...
2221
+ [2025-08-23 02:22:41,533][13958] Avg episode rewards: #0: 6.590, true rewards: #0: 4.340
2222
+ [2025-08-23 02:22:41,534][13958] Avg episode reward: 6.590, avg true_objective: 4.340
2223
+ [2025-08-23 02:22:41,611][13958] Num frames 1800...
2224
+ [2025-08-23 02:22:41,731][13958] Num frames 1900...
2225
+ [2025-08-23 02:22:41,853][13958] Num frames 2000...
2226
+ [2025-08-23 02:22:41,974][13958] Num frames 2100...
2227
+ [2025-08-23 02:22:42,053][13958] Avg episode rewards: #0: 6.040, true rewards: #0: 4.240
2228
+ [2025-08-23 02:22:42,054][13958] Avg episode reward: 6.040, avg true_objective: 4.240
2229
+ [2025-08-23 02:22:42,151][13958] Num frames 2200...
2230
+ [2025-08-23 02:22:42,272][13958] Num frames 2300...
2231
+ [2025-08-23 02:22:42,395][13958] Num frames 2400...
2232
+ [2025-08-23 02:22:42,512][13958] Num frames 2500...
2233
+ [2025-08-23 02:22:42,572][13958] Avg episode rewards: #0: 5.673, true rewards: #0: 4.173
2234
+ [2025-08-23 02:22:42,573][13958] Avg episode reward: 5.673, avg true_objective: 4.173
2235
+ [2025-08-23 02:22:42,686][13958] Num frames 2600...
2236
+ [2025-08-23 02:22:42,807][13958] Num frames 2700...
2237
+ [2025-08-23 02:22:42,927][13958] Num frames 2800...
2238
+ [2025-08-23 02:22:43,048][13958] Num frames 2900...
2239
+ [2025-08-23 02:22:43,178][13958] Num frames 3000...
2240
+ [2025-08-23 02:22:43,301][13958] Num frames 3100...
2241
+ [2025-08-23 02:22:43,370][13958] Avg episode rewards: #0: 6.589, true rewards: #0: 4.446
2242
+ [2025-08-23 02:22:43,371][13958] Avg episode reward: 6.589, avg true_objective: 4.446
2243
+ [2025-08-23 02:22:43,476][13958] Num frames 3200...
2244
+ [2025-08-23 02:22:43,597][13958] Num frames 3300...
2245
+ [2025-08-23 02:22:43,719][13958] Num frames 3400...
2246
+ [2025-08-23 02:22:43,841][13958] Num frames 3500...
2247
+ [2025-08-23 02:22:43,963][13958] Num frames 3600...
2248
+ [2025-08-23 02:22:44,096][13958] Avg episode rewards: #0: 6.831, true rewards: #0: 4.581
2249
+ [2025-08-23 02:22:44,099][13958] Avg episode reward: 6.831, avg true_objective: 4.581
2250
+ [2025-08-23 02:22:44,155][13958] Num frames 3700...
2251
+ [2025-08-23 02:22:44,273][13958] Num frames 3800...
2252
+ [2025-08-23 02:22:44,411][13958] Num frames 3900...
2253
+ [2025-08-23 02:22:44,545][13958] Num frames 4000...
2254
+ [2025-08-23 02:22:44,667][13958] Num frames 4100...
2255
+ [2025-08-23 02:22:44,787][13958] Num frames 4200...
2256
+ [2025-08-23 02:22:44,908][13958] Num frames 4300...
2257
+ [2025-08-23 02:22:45,028][13958] Num frames 4400...
2258
+ [2025-08-23 02:22:45,161][13958] Num frames 4500...
2259
+ [2025-08-23 02:22:45,283][13958] Num frames 4600...
2260
+ [2025-08-23 02:22:45,369][13958] Avg episode rewards: #0: 8.470, true rewards: #0: 5.137
2261
+ [2025-08-23 02:22:45,369][13958] Avg episode reward: 8.470, avg true_objective: 5.137
2262
+ [2025-08-23 02:22:45,463][13958] Num frames 4700...
2263
+ [2025-08-23 02:22:45,585][13958] Num frames 4800...
2264
+ [2025-08-23 02:22:45,706][13958] Num frames 4900...
2265
+ [2025-08-23 02:22:45,828][13958] Num frames 5000...
2266
+ [2025-08-23 02:22:45,966][13958] Num frames 5100...
2267
+ [2025-08-23 02:22:46,137][13958] Num frames 5200...
2268
+ [2025-08-23 02:22:46,340][13958] Num frames 5300...
2269
+ [2025-08-23 02:22:46,507][13958] Num frames 5400...
2270
+ [2025-08-23 02:22:46,657][13958] Avg episode rewards: #0: 9.355, true rewards: #0: 5.455
2271
+ [2025-08-23 02:22:46,658][13958] Avg episode reward: 9.355, avg true_objective: 5.455
2272
+ [2025-08-23 02:23:16,504][13958] Replay video saved to /content/train_dir/default_experiment/replay.mp4!