From 149278d2c6f5fc63e3ce8c6988d98ac0eb244338 Mon Sep 17 00:00:00 2001
From: Josh Creek <8179928+jcreek@users.noreply.github.com>
Date: Tue, 28 Nov 2023 20:59:48 +0000
Subject: [PATCH] Commit latest version before changing to amd gpu

---
 rlgym training/.vscode/launch.json   | 16 +++++
 rlgym training/bot/src/agent.py      |  2 +-
 rlgym training/bot/src/bot.py        |  8 ++-
 rlgym training/requirements.txt      | 96 ++++++----------------------
 rlgym training/rlgym-ppo-training.py |  8 ++-
 5 files changed, 47 insertions(+), 83 deletions(-)
 create mode 100644 rlgym training/.vscode/launch.json

diff --git a/rlgym training/.vscode/launch.json b/rlgym training/.vscode/launch.json
new file mode 100644
index 0000000..2b2502c
--- /dev/null
+++ b/rlgym training/.vscode/launch.json	
@@ -0,0 +1,16 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Current File",
+            "type": "python",
+            "request": "launch",
+            "program": "${file}",
+            "console": "integratedTerminal",
+            "justMyCode": false
+        }
+    ]
+}
\ No newline at end of file
diff --git a/rlgym training/bot/src/agent.py b/rlgym training/bot/src/agent.py
index 285d7ec..50ba8f2 100644
--- a/rlgym training/bot/src/agent.py	
+++ b/rlgym training/bot/src/agent.py	
@@ -72,6 +72,6 @@ class Agent:
 
     def act(self, obs):
         action, logprob = self.policy.get_action(obs, deterministic=False)
-        action = self.actor.eval(obs)
+        # action = self.policy.eval(obs)
         # action, _ = self.model.predict(obs)
         return action.tolist()
diff --git a/rlgym training/bot/src/bot.py b/rlgym training/bot/src/bot.py
index ba14ce2..e558b8b 100644
--- a/rlgym training/bot/src/bot.py	
+++ b/rlgym training/bot/src/bot.py	
@@ -9,7 +9,9 @@ from agent import Agent
 # from obs.default_obs import DefaultObs
 from rlgym.utils.obs_builders import AdvancedObs
 from rlgym_compat import GameState
-from rlgym.utils.action_parsers import ContinuousAction
+
+# from rlgym.utils.action_parsers import ContinuousAction
+from rlgym_tools.extra_action_parsers.lookup_act import LookupAction
 
 from rlgym_tools.extra_obs.advanced_padder import AdvancedObsPadder
 
@@ -20,9 +22,9 @@ class Sarpy(BaseAgent):
 
         # FIXME Hey, botmaker. Start here:
         # Swap the obs builder if you are using a different one, RLGym's AdvancedObs is also available
-        self.obs_builder = AdvancedObsPadder(team_size=3)
+        self.obs_builder = AdvancedObsPadder(team_size=1)
         # Swap the action parser if you are using a different one, RLGym's Discrete and Continuous are also available
-        self.act_parser = ContinuousAction()
+        self.act_parser = LookupAction()
         # Your neural network logic goes inside the Agent class, go take a look inside src/agent.py
         self.agent = Agent()
         # Adjust the tickskip if your agent was trained with a different value
diff --git a/rlgym training/requirements.txt b/rlgym training/requirements.txt
index 3489cd8..aa6b3f8 100644
--- a/rlgym training/requirements.txt	
+++ b/rlgym training/requirements.txt	
@@ -1,90 +1,34 @@
-appdirs==1.4.4
-attrs==23.1.0
-bottle==0.12.25
-bottle-websocket==0.2.9
-certifi==2022.12.7
-cffi==1.16.0
-charset-normalizer==2.1.1
-click==8.1.7
+absl-py==2.0.0
+cachetools==5.3.1
+certifi==2023.7.22
+charset-normalizer==3.3.0
 cloudpickle==3.0.0
-colorama==0.4.6
 comtypes==1.2.0
-dataclasses==0.6
-docker-pycreds==0.4.0
-docopt==0.6.2
-Eel==0.16.0
-exceptiongroup==1.1.3
-filelock==3.9.0
-flatbuffers==1.12
-fsspec==2023.4.0
-future==0.18.3
-gevent==23.9.1
-gevent-websocket==0.10.1
-gitdb==4.0.11
-GitPython==3.1.40
-greenlet==3.0.0
+google-auth==2.23.3
+google-auth-oauthlib==1.0.0
+grpcio==1.59.0
 gym==0.26.2
 gym-notices==0.0.8
-h11==0.14.0
 idna==3.4
 importlib-metadata==6.8.0
-inputs==0.5
-Jinja2==3.1.2
-llvmlite==0.38.1
-MarkupSafe==2.1.2
-mpmath==1.3.0
-networkx==3.0
-numba==0.55.1
-numpy==1.21.6
-outcome==1.3.0
-packaging==23.2
-pathtools==0.1.2
-Pillow==9.3.0
+Markdown==3.5
+MarkupSafe==2.1.3
+numpy==1.26.1
+oauthlib==3.2.2
 protobuf==4.24.4
 psutil==5.9.6
-pycparser==2.21
-pyparsing==3.1.1
-PyQt5==5.15.10
-PyQt5-Qt5==5.15.2
-PyQt5-sip==12.13.0
-PySocks==1.7.1
-python-dotenv==1.0.0
+pyasn1==0.5.0
+pyasn1-modules==0.3.0
 pywin32==228
 pywinauto==0.6.8
-PyYAML==6.0.1
-requests==2.28.1
-requirements-parser==0.5.0
-rlbot==1.67.7
-rlbot-gui==0.0.154
+requests==2.31.0
+requests-oauthlib==1.3.1
 rlgym==1.2.2
-rlgym-compat==1.1.0
-rlgym-ppo==1.2.5
-rlgym-sim==1.2.5
 rlgym-tools==1.8.2
-RLUtilities==0.0.13
-RocketSim==1.2.0
-scipy==1.11.3
-selenium==4.14.0
-sentry-sdk==1.32.0
-setproctitle==1.3.3
+rsa==4.9
 six==1.16.0
-smmap==5.0.1
-sniffio==1.3.0
-sortedcontainers==2.4.0
-sympy==1.12
-torch==2.1.0+cu118
-torchaudio==2.1.0+cu118
-torchvision==0.16.0+cu118
-trio==0.22.2
-trio-websocket==0.11.1
-types-setuptools==68.2.0.0
-typing-extensions==4.8.0
-urllib3==1.26.13
-wandb==0.15.12
-webdriver-manager==4.0.1
-websockets==12.0
-whichcraft==0.6.1
-wsproto==1.2.0
+tensorboard==2.14.1
+tensorboard-data-server==0.7.1
+urllib3==2.0.6
+werkzeug==3.0.0
 zipp==3.17.0
-zope.event==5.0
-zope.interface==6.1
diff --git a/rlgym training/rlgym-ppo-training.py b/rlgym training/rlgym-ppo-training.py
index 5aa4885..ea7ffde 100644
--- a/rlgym training/rlgym-ppo-training.py	
+++ b/rlgym training/rlgym-ppo-training.py	
@@ -42,7 +42,9 @@ def build_rocketsim_env():
         GoalScoredCondition,
     )
     from rlgym_sim.utils import common_values
-    from rlgym_sim.utils.action_parsers import ContinuousAction
+
+    # from rlgym_sim.utils.action_parsers import ContinuousAction
+    from rlgym_tools.extra_action_parsers.lookup_act import LookupAction
     from rlgym_tools.extra_obs.advanced_padder import AdvancedObsPadder
 
     spawn_opponents = True
@@ -52,7 +54,7 @@ def build_rocketsim_env():
     timeout_seconds = 10
     timeout_ticks = int(round(timeout_seconds * game_tick_rate / tick_skip))
 
-    action_parser = ContinuousAction()
+    action_parser = LookupAction()
     terminal_conditions = [
         NoTouchTimeoutCondition(timeout_ticks),
         GoalScoredCondition(),
@@ -177,7 +179,7 @@ if __name__ == "__main__":
             if checkpoint_load_folder != ""
             else {}
         ),
-        timestep_limit=1_000_000_000,
+        timestep_limit=100_000_000_000,
         log_to_wandb=True,
         n_checkpoints_to_keep=10_000,
     )