Merge branch 'main' of https://github.com/boettiger-lab/caribou-rl

.github/workflows/run-tests.yml

@@ -0,0 +1,44 @@
+name: Pytest unit/integration
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+
+# Use bash by default in all jobs
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  build-test:
+    name: Test Run (${{ matrix.python-version }}, ${{ matrix.os }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: ["ubuntu-latest"]
+#        os: ["ubuntu-latest", "macos-latest", "windows-latest"]
+        python-version: ["3.10", "3.11"]
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install nox
+      - name: List installed packages
+        run: pip list
+      - name: Run tests with pytest & nox
+        run: |
+          nox -s test-${{ matrix.python-version }}
+#  Codecov is only free for open source / public repos. Not really needed anyway   
+#      - name: Upload coverage to Codecov
+#        if: ${{ matrix.os == 'ubuntu-latest' &&  matrix.python-version == '3.10'}}
+#        uses: codecov/codecov-action@v3
+

.gitignore

@@ -135,5 +135,8 @@ dmypy.json
 # cache
 venv/
 *.gz
+*.zip
+
+manuscript/*.pdf
+
 
-manuscript/*.pdf

hyperpars/ppo-caribou-v0-1.yml

@@ -0,0 +1,11 @@
+# stable-baselines3 configuration
+
+algo: "PPO"
+env_id: "Caribou-v0"
+n_envs: 12
+tensorboard: "/home/rstudio/logs"
+total_timesteps: 6000000
+config: {}
+use_sde: True
+id: "1"
+repo: "cboettig/rl-ecology"

hyperpars/rllib/ppo-asm.yml

@@ -0,0 +1,30 @@
+asm:
+    env: rl4fisheries.asm.Asm
+    run: PPO
+    stop:
+        time_total_s: 24000
+    config:
+        lambda: 0.95
+        kl_coeff: 0.5
+        clip_param: 0.2
+        vf_clip_param: 400.0
+        entropy_coeff: 0.0001
+        rollout_fragment_length: auto
+        num_sgd_iter: 10
+        num_envs_per_worker: 24
+        min_time_s_per_iteration: 360
+        lr: 0.0003
+
+        # Run with Learner- and RLModule API (new stack).
+        _enable_learner_api: true
+        _enable_rl_module_api: true
+        # Use N Learner worker on the GPU
+        num_learner_workers: 2
+        num_gpus_per_learner_worker: 1
+        num_gpus: 0  # No GPU needed for driver.
+        # Since we are using learner workers, the driver process does not need
+        # a CPU in particular.
+        num_cpus_for_local_worker: 1
+        # Need to unset this b/c we are using the RLModule API, which
+        # provides exploration control via the RLModule's `forward_exploration` method.
+        exploration_config: {}

hyperpars/tqc-caribou-v0-1.yml

@@ -0,0 +1,11 @@
+# stable-baselines3 configuration
+
+algo: "TQC"
+env_id: "Caribou-v0"
+n_envs: 12
+tensorboard: "/home/rstudio/logs"
+total_timesteps: 6000000
+config: {}
+use_sde: True
+id: "1"
+repo: "cboettig/rl-ecology"