PPO playing PongNoFrameskip-v4 from https://github.com/sgoodfriend/rl-algo-impls/tree/e47a44c4d891f48885af0b1605b30d19fc67b5af

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: rl-algo-impls
 tags:
-- impala-PongNoFrameskip-v4
+- PongNoFrameskip-v4
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -16,12 +16,12 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: impala-PongNoFrameskip-v4
-      type: impala-PongNoFrameskip-v4
+      name: PongNoFrameskip-v4
+      type: PongNoFrameskip-v4
 ---
-# **PPO** Agent playing **impala-PongNoFrameskip-v4**
+# **PPO** Agent playing **PongNoFrameskip-v4**
 
-This is a trained model of a **PPO** agent playing **impala-PongNoFrameskip-v4** using the [/sgoodfriend/rl-algo-impls](https://github.com/sgoodfriend/rl-algo-impls) repo.
+This is a trained model of a **PPO** agent playing **PongNoFrameskip-v4** using the [/sgoodfriend/rl-algo-impls](https://github.com/sgoodfriend/rl-algo-impls) repo.
 
 All models trained at this commit can be found at https://api.wandb.ai/links/sgoodfriend/v4wd7cp5.
 
@@ -32,7 +32,7 @@ This model was trained from 3 trainings of **PPO** agents using different initia
 | algo   | env                |   seed |   reward_mean |   reward_std |   eval_episodes | best   | wandb_url                                                                    |
 |:-------|:-------------------|-------:|--------------:|-------------:|----------------:|:-------|:-----------------------------------------------------------------------------|
 | ppo    | PongNoFrameskip-v4 |      1 |        21     |     0        |              16 | *      | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/2bvab97i) |
-| ppo    | PongNoFrameskip-v4 |      2 |        20.875 |     0.484123 |              16 |        | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/hjag7zwi) |
+| ppo    | PongNoFrameskip-v4 |      2 |        20.875 |     0.330719 |              16 |        | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/hjag7zwi) |
 | ppo    | PongNoFrameskip-v4 |      3 |        21     |     0        |              16 |        | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/197tllk4) |
 
 
@@ -72,7 +72,7 @@ commit the agent was trained on: [e47a44c](https://github.com/sgoodfriend/rl-alg
 training is deterministic, different hardware will give different results.
 
 ```
-python train.py --algo ppo --env impala-PongNoFrameskip-v4 --seed 1
+python train.py --algo ppo --env PongNoFrameskip-v4 --seed 1
 ```
 
 Setup hasn't been completely worked out yet, so you might be best served by using Google

compare_runs.py

@@ -143,16 +143,16 @@ if __name__ == "__main__":
         help="WandB tag for experiment commit (i.e. benchmark_5540e1f)",
     )
     parser.add_argument(
-        "--exclude_envs",
+        "--exclude-envs",
         type=str,
         nargs="*",
         help="Environments to exclude from comparison",
     )
     # parser.set_defaults(
-    #     wandb_hostname_tag=["host_192-9-145-26"],
-    #     wandb_control_tag=["benchmark_e4d1ed6", "benchmark_5598ebc"],
-    #     wandb_experiment_tag=["benchmark_680043d", "benchmark_5540e1f"],
-    #     exclude_envs=["CarRacing-v0"],
+    #     wandb_hostname_tag=["host_150-230-44-105", "host_155-248-214-128"],
+    #     wandb_control_tag=["benchmark_fbc943f"],
+    #     wandb_experiment_tag=["benchmark_f59bf74"],
+    #     exclude_envs=[],
     # )
     args = parser.parse_args()
     print(args)
@@ -166,15 +166,19 @@ if __name__ == "__main__":
     runs_by_run_group: Dict[RunGroup, RunGroupRuns] = {}
     wandb_hostname_tags = set(args.wandb_hostname_tag)
     for r in all_runs:
+        if r.state != "finished":
+            continue
         wandb_tags = set(r.config.get("wandb_tags", []))
         if not wandb_tags or not wandb_hostname_tags & wandb_tags:
             continue
-        rg = RunGroup(r.config["algo"], r.config["env"])
+        rg = RunGroup(r.config["algo"], r.config.get("env_id") or r.config["env"])
         if args.exclude_envs and rg.env_id in args.exclude_envs:
             continue
         if rg not in runs_by_run_group:
             runs_by_run_group[rg] = RunGroupRuns(
-                rg, args.wandb_control_tag, args.wandb_experiment_tag
+                rg,
+                args.wandb_control_tag,
+                args.wandb_experiment_tag,
             )
         runs_by_run_group[rg].add_run(r)
     df = RunGroupRuns.data_frame(runs_by_run_group.values()).round(decimals=2)

huggingface_publish.py

@@ -38,12 +38,12 @@ def publish(
     api = wandb.Api()
     runs = [api.run(rp) for rp in wandb_run_paths]
     algo = runs[0].config["algo"]
-    env = runs[0].config["env"]
+    hyperparam_id = runs[0].config["env"]
     evaluations = [
         evaluate_model(
             EvalArgs(
                 algo,
-                env,
+                hyperparam_id,
                 seed=r.config.get("seed", None),
                 render=False,
                 best=True,
@@ -80,9 +80,10 @@ def publish(
 
         github_url = "https://github.com/sgoodfriend/rl-algo-impls"
         commit_hash = run_metadata.get("git", {}).get("commit", None)
+        env_id = runs[0].config.get("env_id") or runs[0].config["env"]
         card_text = model_card_text(
             algo,
-            env,
+            env_id,
             github_url,
             commit_hash,
             wandb_report_url,
@@ -97,7 +98,7 @@ def publish(
         metadata = {
             "library_name": "rl-algo-impls",
             "tags": [
-                env,
+                env_id,
                 algo,
                 "deep-reinforcement-learning",
                 "reinforcement-learning",
@@ -119,8 +120,8 @@ def publish(
                                 "name": "reinforcement-learning",
                             },
                             "dataset": {
-                                "name": env,
-                                "type": env,
+                                "name": env_id,
+                                "type": env_id,
                             },
                         }
                     ],
@@ -159,7 +160,7 @@ def publish(
             repo_id=huggingface_repo,
             folder_path=repo_dir_path,
             path_in_repo="",
-            commit_message=f"{algo.upper()} playing {env} from {github_url}/tree/{commit_hash}",
+            commit_message=f"{algo.upper()} playing {env_id} from {github_url}/tree/{commit_hash}",
             token=huggingface_token,
         )
         print(f"Pushed model to the hub: {repo_url}")

replay.meta.json

@@ -1 +1 @@
-{"content_type": "video/mp4", "encoder_version": {"backend": "ffmpeg", "version": "b'ffmpeg version 5.1.2 Copyright (c) 2000-2022 the FFmpeg developers\\nbuilt with clang version 14.0.6\\nconfiguration: --prefix=/Users/runner/miniforge3/conda-bld/ffmpeg_1671040513231/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pl --cc=arm64-apple-darwin20.0.0-clang --cxx=arm64-apple-darwin20.0.0-clang++ --nm=arm64-apple-darwin20.0.0-nm --ar=arm64-apple-darwin20.0.0-ar --disable-doc --disable-openssl --enable-demuxer=dash --enable-hardcoded-tables --enable-libfreetype --enable-libfontconfig --enable-libopenh264 --enable-cross-compile --arch=arm64 --target-os=darwin --cross-prefix=arm64-apple-darwin20.0.0- --host-cc=/Users/runner/miniforge3/conda-bld/ffmpeg_1671040513231/_build_env/bin/x86_64-apple-darwin13.4.0-clang --enable-neon --enable-gnutls --enable-libmp3lame --enable-libvpx --enable-pthreads --enable-gpl --enable-libx264 --enable-libx265 --enable-libaom --enable-libsvtav1 --enable-libxml2 --enable-pic --enable-shared --disable-static --enable-version3 --enable-zlib --pkg-config=/Users/runner/miniforge3/conda-bld/ffmpeg_1671040513231/_build_env/bin/pkg-config\\nlibavutil      57. 28.100 / 57. 28.100\\nlibavcodec     59. 37.100 / 59. 37.100\\nlibavformat    59. 27.100 / 59. 27.100\\nlibavdevice    59.  7.100 / 59.  7.100\\nlibavfilter     8. 44.100 /  8. 44.100\\nlibswscale      6.  7.100 /  6.  7.100\\nlibswresample   4.  7.100 /  4.  7.100\\nlibpostproc    56.  6.100 / 56.  6.100\\n'", "cmdline": ["ffmpeg", "-nostats", "-loglevel", "error", "-y", "-f", "rawvideo", "-s:v", "160x210", "-pix_fmt", "rgb24", "-framerate", "30", "-i", "-", "-vf", "scale=trunc(iw/2)*2:trunc(ih/2)*2", "-vcodec", "libx264", "-pix_fmt", "yuv420p", "-r", "30", "/var/folders/9g/my5557_91xddp6lx00nkzly80000gn/T/tmplpwls4k8/ppo-impala-PongNoFrameskip-v4/replay.mp4"]}, "episode": {"r": 21.0, "l": 8220, "t": 29.493788}}
+{"content_type": "video/mp4", "encoder_version": {"backend": "ffmpeg", "version": "b'ffmpeg version 5.1.2 Copyright (c) 2000-2022 the FFmpeg developers\\nbuilt with clang version 14.0.6\\nconfiguration: --prefix=/Users/runner/miniforge3/conda-bld/ffmpeg_1671040513231/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pl --cc=arm64-apple-darwin20.0.0-clang --cxx=arm64-apple-darwin20.0.0-clang++ --nm=arm64-apple-darwin20.0.0-nm --ar=arm64-apple-darwin20.0.0-ar --disable-doc --disable-openssl --enable-demuxer=dash --enable-hardcoded-tables --enable-libfreetype --enable-libfontconfig --enable-libopenh264 --enable-cross-compile --arch=arm64 --target-os=darwin --cross-prefix=arm64-apple-darwin20.0.0- --host-cc=/Users/runner/miniforge3/conda-bld/ffmpeg_1671040513231/_build_env/bin/x86_64-apple-darwin13.4.0-clang --enable-neon --enable-gnutls --enable-libmp3lame --enable-libvpx --enable-pthreads --enable-gpl --enable-libx264 --enable-libx265 --enable-libaom --enable-libsvtav1 --enable-libxml2 --enable-pic --enable-shared --disable-static --enable-version3 --enable-zlib --pkg-config=/Users/runner/miniforge3/conda-bld/ffmpeg_1671040513231/_build_env/bin/pkg-config\\nlibavutil      57. 28.100 / 57. 28.100\\nlibavcodec     59. 37.100 / 59. 37.100\\nlibavformat    59. 27.100 / 59. 27.100\\nlibavdevice    59.  7.100 / 59.  7.100\\nlibavfilter     8. 44.100 /  8. 44.100\\nlibswscale      6.  7.100 /  6.  7.100\\nlibswresample   4.  7.100 /  4.  7.100\\nlibpostproc    56.  6.100 / 56.  6.100\\n'", "cmdline": ["ffmpeg", "-nostats", "-loglevel", "error", "-y", "-f", "rawvideo", "-s:v", "160x210", "-pix_fmt", "rgb24", "-framerate", "30", "-i", "-", "-vf", "scale=trunc(iw/2)*2:trunc(ih/2)*2", "-vcodec", "libx264", "-pix_fmt", "yuv420p", "-r", "30", "/var/folders/9g/my5557_91xddp6lx00nkzly80000gn/T/tmpy4msmta0/ppo-impala-PongNoFrameskip-v4/replay.mp4"]}, "episode": {"r": 21.0, "l": 8220, "t": 30.25069}}