sabretoothedhugs commited on
Commit
2befa79
·
1 Parent(s): 80a5e58

pong added

Browse files
app.py CHANGED
@@ -393,7 +393,10 @@ def display_choice(algo, game,slider):
393
  mean_scores = test_c51(config_c51)
394
 
395
  case "Pong" :
396
- return 19
 
 
 
397
 
398
  case "FQF":
399
  config_fqf["seed"] = slider
@@ -404,7 +407,9 @@ def display_choice(algo, game,slider):
404
  mean_scores = test_FQF(config_fqf)
405
 
406
  case "Pong" :
407
- return 20
 
 
408
 
409
  case "FQF-Rainbow":
410
  config_fqf_r["seed"] = slider
@@ -415,7 +420,9 @@ def display_choice(algo, game,slider):
415
  mean_scores = test_fqf_rainbow(config_fqf_r)
416
 
417
  case "Pong" :
418
- return 21
 
 
419
 
420
 
421
 
@@ -429,7 +436,7 @@ def display_choice(algo, game,slider):
429
  # Define the choices for the radio buttons
430
  algos = ["C51", "FQF", "FQF-Rainbow"]
431
  # games = ["Pong", "Space Invaders","Freeway","MsPacman"]
432
- games = ["Freeway"]
433
 
434
 
435
  # Create a Gradio Interface
@@ -440,10 +447,10 @@ demo = gr.Interface(
440
  title="Distributional RL Algorithms Benchmark",
441
  description="Select the DRL agent and the game of your choice",
442
  theme="soft",
443
- # examples=[["FQF","Pong",31],
444
- # ["C51","Space Invaders",31],
445
- # ["FQF-Rainbow","Freeway",31]
446
- # ]
447
  )
448
 
449
  # Launch the Gradio app
 
393
  mean_scores = test_c51(config_c51)
394
 
395
  case "Pong" :
396
+ config_c51["resume_path"] = "models/c51_pong.pth"
397
+ config_c51["task"] = "PongNoFrameskip-v4"
398
+ mean_scores = test_c51(config_c51)
399
+
400
 
401
  case "FQF":
402
  config_fqf["seed"] = slider
 
407
  mean_scores = test_FQF(config_fqf)
408
 
409
  case "Pong" :
410
+ config_fqf["resume_path"] = "models/fqf_pong.pth"
411
+ config_fqf["task"] = "PongNoFrameskip-v4"
412
+ mean_scores = test_FQF(config_fqf)
413
 
414
  case "FQF-Rainbow":
415
  config_fqf_r["seed"] = slider
 
420
  mean_scores = test_fqf_rainbow(config_fqf_r)
421
 
422
  case "Pong" :
423
+ config_fqf_r["resume_path"] = "models/fqf-rainbow_pong.pth"
424
+ config_fqf_r["task"] = "PongNoFrameskip-v4"
425
+ mean_scores = test_fqf_rainbow(config_fqf_r)
426
 
427
 
428
 
 
436
  # Define the choices for the radio buttons
437
  algos = ["C51", "FQF", "FQF-Rainbow"]
438
  # games = ["Pong", "Space Invaders","Freeway","MsPacman"]
439
+ games = ["Freeway","Pong"]
440
 
441
 
442
  # Create a Gradio Interface
 
447
  title="Distributional RL Algorithms Benchmark",
448
  description="Select the DRL agent and the game of your choice",
449
  theme="soft",
450
+ examples=[["FQF","Pong",31],
451
+ ["C51","Freeway",31],
452
+ ["FQF-Rainbow","Freeway",31]
453
+ ]
454
  )
455
 
456
  # Launch the Gradio app
models/c51_pong.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb1c19a7ba5a20837b23f3d35e0887ccb872dcf046272baf234de90afee2079e
3
+ size 14735486
models/fqf-rainbow_pong.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6f5f6f11294aecb49492be954b2cb55c2f1f3f1dfcf0c8b0844dc10c9d5c68
3
+ size 67072998
models/fqf_pong.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b5790f7beec93552a965aa3d877cd381103bf8d8c8132e155c9c8e965ad7d2
3
+ size 15538854
video-app/rl-video-episode-0.mp4 CHANGED
Binary files a/video-app/rl-video-episode-0.mp4 and b/video-app/rl-video-episode-0.mp4 differ
 
video-app/rl-video-episode-1.meta.json CHANGED
@@ -1 +1 @@
1
- {"step_id": 2044, "episode_id": 1, "content_type": "video/mp4"}
 
1
+ {"step_id": 1647, "episode_id": 1, "content_type": "video/mp4"}
video-app/rl-video-episode-1.mp4 CHANGED
Binary files a/video-app/rl-video-episode-1.mp4 and b/video-app/rl-video-episode-1.mp4 differ