{"id":20512039,"url":"https://github.com/wardlt/molecular-dqn","last_synced_at":"2025-07-15T12:07:03.064Z","repository":{"id":91621851,"uuid":"244683555","full_name":"WardLT/molecular-dqn","owner":"WardLT","description":"A minimal example for running molecular DQNs","archived":false,"fork":false,"pushed_at":"2020-03-03T16:21:23.000Z","size":17,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-05T22:44:48.750Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/WardLT.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-03-03T16:17:10.000Z","updated_at":"2020-03-03T16:21:25.000Z","dependencies_parsed_at":null,"dependency_job_id":"219ed686-8e78-4e04-9ca2-ed165f7c56b1","html_url":"https://github.com/WardLT/molecular-dqn","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/WardLT/molecular-dqn","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WardLT%2Fmolecular-dqn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WardLT%2Fmolecular-dqn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WardLT%2Fmolecular-dqn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WardLT%2Fmolecular-dqn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/WardLT","download_url":"https://codeload.github.com/WardLT/molecular-dqn/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/WardLT%2Fmolecular-dqn/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265434812,"owners_count":23764592,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-15T20:39:29.221Z","updated_at":"2025-07-15T12:07:03.006Z","avatar_url":"https://github.com/WardLT.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Molecular Gym Environment\n\nMinimal port of the [MolDQN approach of Zhou et al.](http://www.nature.com/articles/s41598-019-47148-x) from Tensorflow with a custom environment description to Keras with OpenAI Gym environment specifications.\n\nThis port is currently missing the bootstrapped version of the DQN used by Zhou et al.\n\n**DISCLAIMER**: The main logic for this package is copied from [Google's implementation of DQN](https://github.com/google-research/google-research/blob/master/mol_dqn/chemgraph/dqn/molecules.py). \nFiles directly taken from Google's repository are marked with the original Google copyright and license headers in the files.\n\n## Installation\n\nThe necessary packages for running this package are listed in `electrolyte_env.yml`.\nInstall them with Conda:\n\n```bash\nconda env create --file electrolyte_env.yml\n```\n\n## Training the RL Agent\n\nThe `run_rl.py` script trains the RL agent and has a few command line options for expeirmenting with the training process.\nRun `python run_rl.py --help` to see the command line options.\n\nRunning the script with default settings (i.e., `python run_rl.py`) should take less than 10 minutes.\n\nEach run of this agent will produce a subdirectory of `./rl_tests/` that contains the configuration used for the experiment\nand a log containing records at each step:\n\n- `episode`: Episode number\n- `step`: Step number within that episode\n- `epsilon`: Degree of randomness used in selecting next step\n- `smiles`: State of th emolecule after choosing an action in this step\n- `reward`: Observed reward value for choosing that action\n- `loss`: Training loss for the Q network at each step\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwardlt%2Fmolecular-dqn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwardlt%2Fmolecular-dqn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwardlt%2Fmolecular-dqn/lists"}