From 33d2ecc26a4ac125607477c0a2846afa1b6fc728 Mon Sep 17 00:00:00 2001 From: Marek Wolan Date: Mon, 26 Feb 2024 16:58:43 +0000 Subject: [PATCH] Apply suggestions from code review. --- docs/source/environment.rst | 2 +- .../config/_package_data/example_config_2_rl_agents.yaml | 8 +++++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/docs/source/environment.rst b/docs/source/environment.rst index 87e7f060..2b76572d 100644 --- a/docs/source/environment.rst +++ b/docs/source/environment.rst @@ -7,4 +7,4 @@ RL environments are the objects that directly interface with RL libraries such a * Ray Single agent API - For training a single Ray RLLib agent * Ray MARL API - For training multi-agent systems with Ray RLLib. ``PrimaiteRayMARLEnv`` adheres to the `Official Ray documentation `_. -There is a Jupyter notebook which demonstrates integration with each of these three environments. They are located in ``~/primaite//notebooks/example_notebooks``. +There are Jupyter notebooks which demonstrate integration with each of these three environments. They are located in ``~/primaite//notebooks/example_notebooks``. diff --git a/src/primaite/config/_package_data/example_config_2_rl_agents.yaml b/src/primaite/config/_package_data/example_config_2_rl_agents.yaml index 1ccd7b38..c1e077be 100644 --- a/src/primaite/config/_package_data/example_config_2_rl_agents.yaml +++ b/src/primaite/config/_package_data/example_config_2_rl_agents.yaml @@ -1,11 +1,17 @@ training_config: rl_framework: RLLIB_multi_agent - # rl_framework: SB3 + rl_algorithm: PPO + seed: 333 + n_learn_episodes: 1 + n_eval_episodes: 5 + max_steps_per_episode: 256 + deterministic_eval: false n_agents: 2 agent_references: - defender_1 - defender_2 + io_settings: save_checkpoints: true checkpoint_interval: 5