{"id":28381117,"url":"https://github.com/humancompatibleai/learning_biases","last_synced_at":"2026-02-27T09:11:06.768Z","repository":{"id":73455343,"uuid":"105069578","full_name":"HumanCompatibleAI/learning_biases","owner":"HumanCompatibleAI","description":"Infer how suboptimal agents are suboptimal while planning, for example if they are hyperbolic time discounters.","archived":false,"fork":false,"pushed_at":"2020-09-26T15:33:44.000Z","size":2713,"stargazers_count":25,"open_issues_count":0,"forks_count":11,"subscribers_count":7,"default_branch":"master","last_synced_at":"2025-06-25T01:44:28.865Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/HumanCompatibleAI.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,"zenodo":null}},"created_at":"2017-09-27T21:07:51.000Z","updated_at":"2025-06-02T21:21:49.000Z","dependencies_parsed_at":"2023-03-05T15:45:45.566Z","dependency_job_id":null,"html_url":"https://github.com/HumanCompatibleAI/learning_biases","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/HumanCompatibleAI/learning_biases","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HumanCompatibleAI%2Flearning_biases","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HumanCompatibleAI%2Flearning_biases/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HumanCompatibleAI%2Flearning_biases/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HumanCompatibleAI%2Flearning_biases/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/HumanCompatibleAI","download_url":"https://codeload.github.com/HumanCompatibleAI/learning_biases/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HumanCompatibleAI%2Flearning_biases/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29889047,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-27T08:34:21.514Z","status":"ssl_error","status_checked_at":"2026-02-27T08:32:38.035Z","response_time":57,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":"2025-05-30T03:38:10.347Z","updated_at":"2026-02-27T09:11:06.763Z","avatar_url":"https://github.com/HumanCompatibleAI.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"_Last updated Oct 12, 2017_\n\n# planner-inference\nInfer how suboptimal agents are suboptimal while planning, for example if they\nare hyperbolic time discounters. Use this to do better inverse reinforcement\nlearning.\n\n## Code\n\nNote that for **SIMPLE** baseline only gridsizes of 8 \u0026 14 work.\n\nTo run benchmark testing, run `python run_benchmarks.py --low LOW --high HIGH` etc.\n\n\n### Gridworlds\n\n`gridworld.py`: Implements the Gridworld MDP, which is used for simple\nexperiments.\n\n`gridworld_data.py`: Generates example gridworlds, runs agents on the gridworlds\nto generate trajectories, and collects all of the trajectories and puts them\ninto training and test sets used for learning.\n\n### Agents\n\n`agent_interface.py`: Defines the interface that agents should follow.\n\n`agent_runner.py`: Defines `run_agent`, which given an agent and an environment,\nruns the agent in the environment, producing a trajectory.\n\n`agents.py`: Defines many different agents that can play tabular MDPs. Currently\nthe agents are using value iteration like approaches.\n\n### Value Iteration Networks\n\nThe code here is taken from [Tensorflow\nVINs](https://github.com/TheAbhiKumar/tensorflow-value-iteration-networks) with\na few edits.\n\n`model.py`: Implementation of VIN and VIN with untied weights.\n\n`train.py`: Trains a VIN using gridworld data.\n\n### Other\n\n`disjoint_sets.py`: An implementation of the disjoint sets data structure, used in `gridworld_data.py` to generate interesting grid worlds.\n\n`utils.py`: Utility functions.\n\n### Testing\n\nAll of the `*_tests.py` contain tests for the corresponding `*.py` file. All of\nthe tests can be run using:\n\n    ./run_tests.sh\n\nYou may need to first give it execute permissions:\n\n    chmod +x run_tests.sh\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhumancompatibleai%2Flearning_biases","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhumancompatibleai%2Flearning_biases","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhumancompatibleai%2Flearning_biases/lists"}