{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":219459693,"defaultBranch":"master","name":"reinforcement-learning","ownerLogin":"vformanyuk","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2019-11-04T09:07:25.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/9018587?v=4","public":true,"private":false,"isOrgOwned":false},"refInfo":{"name":"","listCacheKey":"v0:1679699303.0","currentOid":""},"activityList":{"items":[{"before":"8e3a4f5e0573a97ef8c099c48392197543d5b5d5","after":"d921854cb440c9c495b00b4872a4227d41a86111","ref":"refs/heads/master","pushedAt":"2023-03-24T23:11:36.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vformanyuk","name":"Vadim Formanyuk","path":"/vformanyuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/9018587?s=80&v=4"},"commit":{"message":"update readme","shortMessageHtmlLink":"update readme"}},{"before":"f1b7ad7af2914da8291538da1bc3d49c9b7d4ab6","after":"8e3a4f5e0573a97ef8c099c48392197543d5b5d5","ref":"refs/heads/master","pushedAt":"2023-03-24T23:09:53.000Z","pushType":"pr_merge","commitsCount":3,"pusher":{"login":"vformanyuk","name":"Vadim Formanyuk","path":"/vformanyuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/9018587?s=80&v=4"},"commit":{"message":"Merge pull request #34 from vformanyuk/Distributional_SAC\n\nDistributional Soft Actor Critic","shortMessageHtmlLink":"Merge pull request <a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1640171872\" data-permission-text=\"Title is private\" data-url=\"https://github.com/vformanyuk/reinforcement-learning/issues/34\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/vformanyuk/reinforcement-learning/pull/34/hovercard\" href=\"https://github.com/vformanyuk/reinforcement-learning/pull/34\">#34</a> from vformanyuk/Distributional_SAC"}},{"before":null,"after":"42964704df31effc5abd9ca55c4de882f4583cf1","ref":"refs/heads/Distributional_SAC","pushedAt":"2023-03-24T23:08:23.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"vformanyuk","name":"Vadim Formanyuk","path":"/vformanyuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/9018587?s=80&v=4"},"commit":{"message":"Distributional SAC. Capped Q likelihood","shortMessageHtmlLink":"Distributional SAC. Capped Q likelihood"}},{"before":"1a587039ba74613f0edad740c60194729ac53487","after":"f1b7ad7af2914da8291538da1bc3d49c9b7d4ab6","ref":"refs/heads/master","pushedAt":"2023-03-21T23:05:23.000Z","pushType":"pr_merge","commitsCount":2,"pusher":{"login":"vformanyuk","name":"Vadim Formanyuk","path":"/vformanyuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/9018587?s=80&v=4"},"commit":{"message":"Merge pull request #33 from vformanyuk/N_step_return\n\nn-step return","shortMessageHtmlLink":"Merge pull request <a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1634815258\" data-permission-text=\"Title is private\" data-url=\"https://github.com/vformanyuk/reinforcement-learning/issues/33\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/vformanyuk/reinforcement-learning/pull/33/hovercard\" href=\"https://github.com/vformanyuk/reinforcement-learning/pull/33\">#33</a> from vformanyuk/N_step_return"}},{"before":"1a587039ba74613f0edad740c60194729ac53487","after":"2e23c2eb478b09122bc868eddc9477bfa974ec1b","ref":"refs/heads/N_step_return","pushedAt":"2023-03-21T23:03:14.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vformanyuk","name":"Vadim Formanyuk","path":"/vformanyuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/9018587?s=80&v=4"},"commit":{"message":"use correct next states, code cleanup","shortMessageHtmlLink":"use correct next states, code cleanup"}},{"before":null,"after":"1a587039ba74613f0edad740c60194729ac53487","ref":"refs/heads/N_step_return","pushedAt":"2023-03-20T22:24:19.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"vformanyuk","name":"Vadim Formanyuk","path":"/vformanyuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/9018587?s=80&v=4"},"commit":{"message":"Merge pull request #32 from vformanyuk/RND_Curiosity_refactoring\n\nCorrect (but slow) implementation of running statistics for RND curiosity","shortMessageHtmlLink":"Merge pull request <a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1619972672\" data-permission-text=\"Title is private\" data-url=\"https://github.com/vformanyuk/reinforcement-learning/issues/32\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/vformanyuk/reinforcement-learning/pull/32/hovercard\" href=\"https://github.com/vformanyuk/reinforcement-learning/pull/32\">#32</a> from vformanyuk/RND_Curiosity_refactoring"}},{"before":"a100b0f4a4ba483a29fe5026b353a8220fa78021","after":null,"ref":"refs/heads/RND_Curiosity_refactoring","pushedAt":"2023-03-14T20:59:46.708Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"vformanyuk","name":"Vadim Formanyuk","path":"/vformanyuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/9018587?s=80&v=4"}},{"before":"c979607c0c58c7a841258a51e3867c9db1a41559","after":"1a587039ba74613f0edad740c60194729ac53487","ref":"refs/heads/master","pushedAt":"2023-03-14T20:59:39.824Z","pushType":"pr_merge","commitsCount":4,"pusher":{"login":"vformanyuk","name":"Vadim Formanyuk","path":"/vformanyuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/9018587?s=80&v=4"},"commit":{"message":"Merge pull request #32 from vformanyuk/RND_Curiosity_refactoring\n\nCorrect (but slow) implementation of running statistics for RND curiosity","shortMessageHtmlLink":"Merge pull request <a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1619972672\" data-permission-text=\"Title is private\" data-url=\"https://github.com/vformanyuk/reinforcement-learning/issues/32\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/vformanyuk/reinforcement-learning/pull/32/hovercard\" href=\"https://github.com/vformanyuk/reinforcement-learning/pull/32\">#32</a> from vformanyuk/RND_Curiosity_refactoring"}},{"before":"3058e9176ea5852a8b4548a920541a75debc9bdb","after":"a100b0f4a4ba483a29fe5026b353a8220fa78021","ref":"refs/heads/RND_Curiosity_refactoring","pushedAt":"2023-03-14T20:47:53.225Z","pushType":"push","commitsCount":1,"pusher":{"login":"vformanyuk","name":"Vadim Formanyuk","path":"/vformanyuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/9018587?s=80&v=4"},"commit":{"message":"Get rid of layer norms and non-running-statistic methods","shortMessageHtmlLink":"Get rid of layer norms and non-running-statistic methods"}},{"before":"6c2d157529ce76916fc64a4514d4c2db5432fa7b","after":"3058e9176ea5852a8b4548a920541a75debc9bdb","ref":"refs/heads/RND_Curiosity_refactoring","pushedAt":"2023-03-11T12:04:33.203Z","pushType":"push","commitsCount":1,"pusher":{"login":"vformanyuk","name":"Vadim Formanyuk","path":"/vformanyuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/9018587?s=80&v=4"},"commit":{"message":"Use layer norm as an alternative","shortMessageHtmlLink":"Use layer norm as an alternative"}},{"before":null,"after":"6c2d157529ce76916fc64a4514d4c2db5432fa7b","ref":"refs/heads/RND_Curiosity_refactoring","pushedAt":"2023-03-11T11:17:37.196Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"vformanyuk","name":"Vadim Formanyuk","path":"/vformanyuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/9018587?s=80&v=4"},"commit":{"message":"Correct (but slow) implementation of running statistics for RND curiosity","shortMessageHtmlLink":"Correct (but slow) implementation of running statistics for RND curio…"}}],"hasNextPage":false,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAADCuVmywA","startCursor":null,"endCursor":null}},"title":"Activity · vformanyuk/reinforcement-learning"}