add examples

benchmarl/evaluate.py

@@ -4,6 +4,7 @@
 #  LICENSE file in the root directory of this source tree.
 #
 import argparse
+from pathlib import Path
 
 from benchmarl.hydra_config import reload_experiment_from_file
 
@@ -15,6 +16,6 @@
         "checkpoint_file", type=str, help="The name of the checkpoint file"
     )
     args = parser.parse_args()
-    checkpoint_file = args.checkpoint_file
+    checkpoint_file = str(Path(args.checkpoint_file).resolve())
     experiment = reload_experiment_from_file(checkpoint_file)
     experiment.evaluate()

benchmarl/resume.py

@@ -6,6 +6,7 @@
 #  LICENSE file in the root directory of this source tree.
 #
 import argparse
+from pathlib import Path
 
 from benchmarl.hydra_config import reload_experiment_from_file
 
@@ -17,7 +18,7 @@
         "checkpoint_file", type=str, help="The name of the checkpoint file"
     )
     args = parser.parse_args()
-    checkpoint_file = args.checkpoint_file
+    checkpoint_file = str(Path(args.checkpoint_file).resolve())
 
     experiment = reload_experiment_from_file(checkpoint_file)
     experiment.run()

examples/evaluate/evalaute_experiment.py

@@ -0,0 +1,26 @@
+#  Copyright (c) Meta Platforms, Inc. and affiliates.
+#
+#  This source code is licensed under the license found in the
+#  LICENSE file in the root directory of this source tree.
+#
+
+from pathlib import Path
+
+from benchmarl.hydra_config import reload_experiment_from_file
+
+if __name__ == "__main__":
+
+    # Let's assume that we have run an experiment with
+    # `python benchmarl/run.py task=vmas/balance algorithm=mappo experiment.max_n_iters=2 experiment.on_policy_collected_frames_per_batch=100 experiment.checkpoint_interval=100`
+    # and we have obtained
+    # "outputs/2024-09-09/20-39-31/mappo_balance_mlp__cd977b69_24_09_09-20_39_31/checkpoints/checkpoint_100.pt""
+
+    # Now we tell it where to restore from
+    current_folder = Path(__file__).parent.absolute()
+    restore_file = (
+        current_folder
+        / "outputs/2024-09-09/20-39-31/mappo_balance_mlp__cd977b69_24_09_09-20_39_31/checkpoints/checkpoint_100.pt"
+    )
+
+    experiment = reload_experiment_from_file(str(restore_file))
+    experiment.evaluate()

examples/evaluate/evaluate_experiment.sh

@@ -0,0 +1,12 @@
+#
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+#
+#
+
+# Assume we have run the experiment with
+# python benchmarl/run.py task=vmas/balance algorithm=mappo experiment.max_n_iters=2 experiment.on_policy_collected_frames_per_batch=100 experiment.checkpoint_interval=100
+# Evaluate it at the given checkpoint
+python benchmarl/evaluate.py ../outputs/2024-09-09/20-39-31/mappo_balance_mlp__cd977b69_24_09_09-20_39_31/checkpoints/checkpoint_100.pt

examples/evaluate/outputs/2024-09-09/20-39-31/.hydra/config.yaml

@@ -0,0 +1,81 @@
+experiment:
+  sampling_device: cpu
+  train_device: cpu
+  buffer_device: cpu
+  share_policy_params: true
+  prefer_continuous_actions: true
+  collect_with_grad: false
+  gamma: 0.9
+  lr: 5.0e-05
+  adam_eps: 1.0e-06
+  clip_grad_norm: true
+  clip_grad_val: 5.0
+  soft_target_update: true
+  polyak_tau: 0.005
+  hard_target_update_frequency: 5
+  exploration_eps_init: 0.8
+  exploration_eps_end: 0.01
+  exploration_anneal_frames: null
+  max_n_iters: 3
+  max_n_frames: 3000000
+  on_policy_collected_frames_per_batch: 100
+  on_policy_n_envs_per_worker: 10
+  on_policy_n_minibatch_iters: 45
+  on_policy_minibatch_size: 400
+  off_policy_collected_frames_per_batch: 6000
+  off_policy_n_envs_per_worker: 10
+  off_policy_n_optimizer_steps: 1000
+  off_policy_train_batch_size: 128
+  off_policy_memory_size: 1000000
+  off_policy_init_random_frames: 0
+  evaluation: true
+  render: true
+  evaluation_interval: 120000
+  evaluation_episodes: 10
+  evaluation_deterministic_actions: true
+  loggers:
+  - csv
+  project_name: benchmarl
+  create_json: true
+  save_folder: null
+  restore_file: null
+  restore_map_location: null
+  checkpoint_interval: 100
+  checkpoint_at_end: false
+  keep_checkpoints_num: 3
+algorithm:
+  share_param_critic: true
+  clip_epsilon: 0.2
+  entropy_coef: 0.0
+  critic_coef: 1.0
+  loss_critic_type: l2
+  lmbda: 0.9
+  scale_mapping: biased_softplus_1.0
+  use_tanh_normal: true
+  minibatch_advantage: false
+task:
+  max_steps: 100
+  n_agents: 4
+  random_package_pos_on_line: true
+  package_mass: 5.0
+model:
+  name: mlp
+  num_cells:
+  - 256
+  - 256
+  layer_class: torch.nn.Linear
+  activation_class: torch.nn.Tanh
+  activation_kwargs: null
+  norm_class: null
+  norm_kwargs: null
+critic_model:
+  name: mlp
+  num_cells:
+  - 256
+  - 256
+  layer_class: torch.nn.Linear
+  activation_class: torch.nn.Tanh
+  activation_kwargs: null
+  norm_class: null
+  norm_kwargs: null
+seed: 0

examples/evaluate/outputs/2024-09-09/20-39-31/.hydra/hydra.yaml

@@ -0,0 +1,164 @@
+hydra:
+  run:
+    dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S}
+  sweep:
+    dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task:
+    - task=vmas/balance
+    - algorithm=mappo
+    - experiment.max_n_iters=3
+    - experiment.on_policy_collected_frames_per_batch=100
+    - experiment.checkpoint_interval=100
+  job:
+    name: run
+    chdir: null
+    override_dirname: algorithm=mappo,experiment.checkpoint_interval=100,experiment.max_n_iters=3,experiment.on_policy_collected_frames_per_batch=100,task=vmas/balance
+    id: ???
+    num: ???
+    config_name: config
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.3'
+    cwd: /Users/Matteo/PycharmProjects/BenchMARL/examples/evaluate
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /Users/Matteo/PycharmProjects/BenchMARL/benchmarl/conf
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /Users/Matteo/PycharmProjects/BenchMARL/examples/evaluate/outputs/2024-09-09/20-39-31
+    choices:
+      model@critic_model: layers/mlp
+      model: layers/mlp
+      task: vmas/balance
+      algorithm: mappo
+      experiment: base_experiment
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: default
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

examples/evaluate/outputs/2024-09-09/20-39-31/.hydra/overrides.yaml

@@ -0,0 +1,5 @@
+- task=vmas/balance
+- algorithm=mappo
+- experiment.max_n_iters=3
+- experiment.on_policy_collected_frames_per_batch=100
+- experiment.checkpoint_interval=100