{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/census/discount-cumsum","entry":"discount_cumsum","source":"Syntology differential census (groundwork/55, run v2_2026-09-22), per sample; not an archive number","census_date":"2026-09-22","battery_sha256":["b986f7e04d794a0d88ad4c5f32cf63ec3590b5deff0192150737bc5f1c0b4677"],"runner_sha256":["5a452d0e7c0da5b80771d1be2afe3572e253568cf5c5d59a0d08ebd663d00808"],"bucket_key":"positional (rank, kind, dtype) of each array argument; the argument name is not part of the key because the harness draws the shared array from (rank, kind) and casts it to the dtype, whatever the name","bucket_fields":["rank","kind","dtype"],"claim":"Implementations sharing this entry name were each run on one shared input fixed by the positional (rank, kind, dtype) of their array arguments (the bucket). A cluster is the set whose recorded output digest (sha256 of the output rounded to 6 decimals) is identical. Identical values to six decimals on the shared input are agreement on those inputs, not a statement about the whole domain and not a substitution claim.","n_implementations_compared":6,"n_papers":13,"n_buckets":3,"n_distinct_outputs":3,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":0,"by_error":{}},"no_array_argument_ran_on_own_fixture_arguments_only":{"n":0,"n_papers":0,"recorded_shared_digest_equals_own_fixture_digest":0},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/discount-cumsum","buckets":[{"bucket":[[1,"float","float64"]],"n_implementations_compared":4,"n_papers":12,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"8b1911efaf6bb986","size":4,"n_papers":12,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":4,"torch_reference_conventions_with_this_digest":[],"values":[-2.4256315385973557,-1.5371136755586596,-1.711358719909064,-2.6353239460345916,-1.892048893523583,-1.7331245760071743,-1.8041982796943805,-0.17753333139257513],"values_recorded":8,"members":[{"code_sha256_prefix":"0161b27cbe3cc58d","path":"oppo/scripted/gym/experiment.py","papers":["2305.16217","2410.11448","2111.10364","2201.12122","2206.01079","2211.14655","2405.17098","2303.07551","2405.20692"],"paper_pages":[{"arxiv_id":"2305.16217","page":"/paper/beyond-reward-offline-preference-guided"},{"arxiv_id":"2410.11448","page":"/paper/meta-dt-offline-meta-rl-as-conditional"},{"arxiv_id":"2111.10364","page":"/paper/generalized-decision-transformer-for-offline"},{"arxiv_id":"2201.12122","page":"/paper/can-wikipedia-help-offline-reinforcement"},{"arxiv_id":"2206.01079","page":"/paper/when-does-return-conditioned-supervised"},{"arxiv_id":"2211.14655","page":"/paper/how-crucial-is-transformer-in-decision"},{"arxiv_id":"2405.17098","page":"/paper/q-value-regularized-transformer-for-offline"},{"arxiv_id":"2303.07551","page":"/paper/merging-decision-transformers-weight"},{"arxiv_id":"2405.20692","page":"/paper/in-context-decision-transformer-reinforcement"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{"gamma":"0.99"},"class_bearing":false},{"code_sha256_prefix":"0d4fc87c387d9018","path":"can-wikipedia-help-offline-rl/experiment.py","papers":["2211.09817"],"paper_pages":[{"arxiv_id":"2211.09817","page":"/paper/on-the-effect-of-pre-training-for-transformer"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{"gamma":"0.99"},"class_bearing":false},{"code_sha256_prefix":"658d370f8dacf5e3","path":"python/rl_loop.py","papers":["2007.02559"],"paper_pages":[{"arxiv_id":"2007.02559","page":"/paper/enhancing-sat-solvers-with-glue-variable"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{"discount":"0.99"},"class_bearing":false},{"code_sha256_prefix":"f047da47c4530c5f","path":"src/all_class.py","papers":["2205.14842"],"paper_pages":[{"arxiv_id":"2205.14842","page":"/paper/efficient-reward-poisoning-attacks-on-online"}],"arg_sig_recorded":[["x",1,"float","float64"]],"scalar_args":{"discount":"0.99"},"class_bearing":false}]}]},{"bucket":[[1,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"8b1911efaf6bb986","size":1,"n_papers":1,"shape":[8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-2.4256317615509033,-1.537113904953003,-1.711358904838562,-2.635324001312256,-1.892048954963684,-1.7331246137619019,-1.8041982650756836,-0.1775333285331726],"values_recorded":8,"members":[{"code_sha256_prefix":"7a477d732661f79a","path":"oppo/human/gym/experiment.py","papers":["2305.16217"],"paper_pages":[{"arxiv_id":"2305.16217","page":"/paper/beyond-reward-offline-preference-guided"}],"arg_sig_recorded":[["x",1,"float","float32"]],"scalar_args":{"gamma":"0.99"},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"],[1,"int","int64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"ccce406cf449a8a6","size":1,"n_papers":1,"shape":[8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-1.0594491423740833,0.15713145715131374,2.7522553138633032,-0.9366885490899604,-0.17625556327648054,1.4911871815919733,-1.4526822835370816,-0.17753333139257513],"values_recorded":8,"members":[{"code_sha256_prefix":"43887c9edd549830","path":"invalid_action_masking/ppo_10x10.py","papers":["2006.14171"],"paper_pages":[{"arxiv_id":"2006.14171","page":"/paper/a-closer-look-at-invalid-action-masking-in"}],"arg_sig_recorded":[["x",1,"float","float64"],["dones",1,"int","int64"]],"scalar_args":{"gamma":"0.99"},"class_bearing":false}]}]}]}