{"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-reward","entry":"discount_reward","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-25T09:33:49+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":5,"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":2,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":1,"unverified":0},"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":"2602.04284","paper":"/paper/arxiv-2602-04284","title":"Agent-Omit: Adaptive Context Omission for Efficient LLM Agents","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"usail-hkust/Agent-Omit","path":"AgentOmit-Gym/agentenv/agentenv-webshop/webshop/baseline_models/agent.py","file_url":"https://github.com/usail-hkust/Agent-Omit/blob/HEAD/AgentOmit-Gym/agentenv/agentenv-webshop/webshop/baseline_models/agent.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c873c43e9aed0a7","mcp_get_code":{"code_sha256":"6c873c43e9aed0a7"}},{"arxiv_id":"2312.05742","paper":"/paper/the-generalization-gap-in-offline","title":"The Generalization Gap in Offline Reinforcement Learning","date":"2023-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/gen_dgrl","path":"webShop/baseline_models/agent.py","file_url":"https://github.com/facebookresearch/gen_dgrl/blob/HEAD/webShop/baseline_models/agent.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c873c43e9aed0a7","mcp_get_code":{"code_sha256":"6c873c43e9aed0a7"}},{"arxiv_id":"2306.02224","paper":"/paper/auto-gpt-for-online-decision-making","title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","date":"2023-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"younghuman/llmagent","path":"webshop/baseline_models/agent.py","file_url":"https://github.com/younghuman/llmagent/blob/HEAD/webshop/baseline_models/agent.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6c873c43e9aed0a7","mcp_get_code":{"code_sha256":"6c873c43e9aed0a7"}},{"arxiv_id":"2207.01206","paper":"/paper/webshop-towards-scalable-real-world-web","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","date":"2022-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/WebShop","path":"baseline_models/agent.py","file_url":"https://github.com/princeton-nlp/WebShop/blob/HEAD/baseline_models/agent.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c873c43e9aed0a7","mcp_get_code":{"code_sha256":"6c873c43e9aed0a7"}},{"arxiv_id":"1903.09338","paper":"/paper/interpretable-reinforcement-learning-via","title":"Optimization Methods for Interpretable Differentiable Decision Trees in Reinforcement Learning","date":"2019-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"core-robotics-lab/interpretable_ddts_aistats2020","path":"interpretable_ddts/opt_helpers/replay_buffer.py","file_url":"https://github.com/core-robotics-lab/interpretable_ddts_aistats2020/blob/HEAD/interpretable_ddts/opt_helpers/replay_buffer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4c77fc22c85ab71e","mcp_get_code":{"code_sha256":"4c77fc22c85ab71e"}}]}