{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"satisfia","owner":"pik-gane","isFork":false,"description":"Satisficing-based Intelligent Agents","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":5,"issueCount":7,"starsCount":3,"forksCount":2,"license":"GNU Affero General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-09-17T00:50:29.652Z"}},{"type":"Public","name":"satisfia-marl","owner":"pik-gane","isFork":true,"description":"A repo to explore multi-agent reinforcement learning in the context of aspiration based, non-maximising agents. This project is part of the Supervised Program for Alignment Research. ","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-08-25T20:09:47.846Z"}},{"type":"Public","name":"pref_voting","owner":"pik-gane","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":4,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-08-08T16:46:24.495Z"}},{"type":"Public","name":"vodle","owner":"pik-gane","isFork":false,"description":"We develop an interactive, consensus-oriented group decision app","allTopics":["svg","couchdb","app","ionic","decision-making","voting","delegation","democracy","consensus","budgeting","hacktoberfest","voting-app","hacktoberfest2023","angular","typescript"],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":6,"issueCount":50,"starsCount":24,"forksCount":14,"license":"GNU Affero General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-28T07:56:32.727Z"}},{"type":"Public","name":"webppl-agents-satisfia","owner":"pik-gane","isFork":true,"description":"Webppl library for generating Gridworld MDPs. JS library for displaying Gridworld. Additional agents that satisfice.","allTopics":[],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":2,"issueCount":0,"starsCount":2,"forksCount":4,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-07T22:40:51.116Z"}},{"type":"Public","name":"cleanrl-satisfia","owner":"pik-gane","isFork":true,"description":"High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":604,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-11T21:54:20.495Z"}},{"type":"Public","name":"stable-baselines3-contrib-satisfia","owner":"pik-gane","isFork":true,"description":"Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":169,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-15T15:53:53.435Z"}},{"type":"Public","name":"rl.pyro-satisfia","owner":"pik-gane","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-04T16:55:30.239Z"}},{"type":"Public","name":"alpaca_farm-collective","owner":"pik-gane","isFork":true,"description":"A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data. ","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":59,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-08-25T12:23:35.626Z"}},{"type":"Public","name":"ai-safety-gridworlds-satisfia","owner":"pik-gane","isFork":true,"description":"This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":120,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-17T14:01:23.612Z"}},{"type":"Public","name":"Minigrid-satisfia","owner":"pik-gane","isFork":true,"description":" Simple and easily configurable grid world environments for reinforcement learning","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":603,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-13T22:16:12.126Z"}},{"type":"Public","name":"pymdptoolbox-satisfia","owner":"pik-gane","isFork":true,"description":"Markov Decision Process (MDP) Toolbox for Python","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":251,"license":"BSD 3-Clause \"New\" or \"Revised\" License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-06-30T20:23:12.333Z"}},{"type":"Public","name":"alpaca_eval-collective","owner":"pik-gane","isFork":true,"description":"A validated automatic evaluator for instruction-following language models. High-quality, cheap, and fast.","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":225,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-06-30T14:22:13.468Z"}},{"type":"Public","name":"motabarnn","owner":"pik-gane","isFork":false,"description":"python package for torch-based neural network version of MoTaBaR","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":6,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-06-21T14:14:37.684Z"}},{"type":"Public","name":"stable-baselines3-satisfia","owner":"pik-gane","isFork":true,"description":"PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms. ","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1660,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-06-13T08:49:21.291Z"}},{"type":"Public","name":"RL4LMs_RLCHF","owner":"pik-gane","isFork":true,"description":"A modular RL library to fine-tune language models to human preferences","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":191,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-31T07:44:39.381Z"}},{"type":"Public","name":"pyoptes","owner":"pik-gane","isFork":false,"description":"Python framework for optimization of epidemic testing strategies","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":"BSD 2-Clause \"Simplified\" License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-12T07:50:10.365Z"}},{"type":"Public","name":"train-procgen-pytorch-satisfia","owner":"pik-gane","isFork":true,"description":"Pytorch implementation on OpenAI's Procgen ppo-baseline, built from scratch.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":24,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-03-13T09:10:23.891Z"}},{"type":"Public","name":"decision-transformer-satisfia","owner":"pik-gane","isFork":true,"description":"Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":440,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-02-03T10:41:34.743Z"}},{"type":"Public","name":"procgenAISC-satisfia","owner":"pik-gane","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":16,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-01-21T17:19:15.549Z"}},{"type":"Public","name":"tricl","owner":"pik-gane","isFork":false,"description":"TriCl model in C++","allTopics":[],"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":0,"issueCount":2,"starsCount":0,"forksCount":0,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-09-23T11:16:19.137Z"}},{"type":"Public","name":"attainable-utility-preservation-satisfia","owner":"pik-gane","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":120,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-01-11T03:07:59.044Z"}},{"type":"Public","name":"pyresponsibility","owner":"pik-gane","isFork":false,"description":"quantify agents' degrees of moral responsibility in complex multi-agent decision situations","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"BSD 2-Clause \"Simplified\" License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-12-15T16:34:12.193Z"}},{"type":"Public","name":"avoiding-side-effects-satisfia","owner":"pik-gane","isFork":true,"description":"Code for reproducing the results from the paper Avoiding Side Effects in Complex Environments","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":2,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-06-03T00:06:29.960Z"}},{"type":"Public","name":"rl-inference-satisfia","owner":"pik-gane","isFork":true,"description":"Reinforcement Learning through Active Inference with additional safety measures","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":20,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-04-27T10:27:35.801Z"}},{"type":"Public","name":"agentmodels-satisfia","owner":"pik-gane","isFork":true,"description":"Modeling agents with probabilistic programs","allTopics":[],"primaryLanguage":{"name":"TeX","color":"#3D6117"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":17,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2019-09-04T17:07:23.217Z"}}],"repositoryCount":26,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"pik-gane repositories"}