{"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":"/code/discount-rewards","entry":"discount_rewards","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":2,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":5,"n_samples_ran":2,"n_samples_fingerprinted":2,"n_places":5,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":2,"ran":0,"unverified":3},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2505.12355","paper":"/paper/gates-cost-aware-dynamic-workflow-scheduling","title":"GATES: Cost-aware Dynamic Workflow Scheduling via Graph Attention Networks and Evolution Strategy","date":"2025-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YaShen998/GATES","path":"assembly/assemble_rl.py","file_url":"https://github.com/YaShen998/GATES/blob/HEAD/assembly/assemble_rl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"21395f0ade1ff348","mcp_get_code":{"code_sha256":"21395f0ade1ff348"}},{"arxiv_id":"2003.01848","paper":"/paper/on-emergent-communication-in-competitive","title":"On Emergent Communication in Competitive Multi-Agent Teams","date":"2020-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pliang279/Competitive-Emergent-Communication","path":"utils.py","file_url":"https://github.com/pliang279/Competitive-Emergent-Communication/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"437f465235e19c8d","mcp_get_code":{"code_sha256":"437f465235e19c8d"}},{"arxiv_id":"1904.00370","paper":"/paper/variational-adversarial-active-learning","title":"Variational Adversarial Active Learning","date":"2019-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"johntiger1/vaal_querying","path":"rl/sample_cartpole.py","file_url":"https://github.com/johntiger1/vaal_querying/blob/HEAD/rl/sample_cartpole.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"afbf4de704d925aa","mcp_get_code":{"code_sha256":"afbf4de704d925aa"}},{"arxiv_id":"1809.02627","paper":"/paper/unity-a-general-platform-for-intelligent","title":"Unity: A General Platform for Intelligent Agents","date":"2018-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xking8/Nav_ml-agent-v5","path":"ml-agents/mlagents/trainers/ppo/trainer.py","file_url":"https://github.com/Xking8/Nav_ml-agent-v5/blob/HEAD/ml-agents/mlagents/trainers/ppo/trainer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c8715f0abed1447a","mcp_get_code":{"code_sha256":"c8715f0abed1447a"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arnomoonens/yarll","path":"yarll/agents/tf1/actorcritic/a3c_worker.py","file_url":"https://github.com/arnomoonens/yarll/blob/HEAD/yarll/agents/tf1/actorcritic/a3c_worker.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9aaf2df19da77344","mcp_get_code":{"code_sha256":"9aaf2df19da77344"}}]}