{"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":"/paper/reconciling-rewards-with-predictive-state","title":"Reconciling Rewards with Predictive State Representations","arxiv_id":"2106.03926","date":"2021-06-07","proceeding":null,"authors":["Andrea Baisero","Christopher Amato"],"abstract":"Predictive state representations (PSRs) are models of controlled non-Markov observation sequences which exhibit the same generative process governing POMDP observations without relying on an underlying latent state. In that respect, a PSR is indistinguishable from the corresponding POMDP. However, PSRs notoriously ignore the notion of rewards, which undermines the general utility of PSR models for control, planning, or reinforcement learning. Therefore, we describe a sufficient and necessary accuracy condition which determines whether a PSR is able to accurately model POMDP rewards, we show that rewards can be approximated even when the accuracy condition is not satisfied, and we find that a non-trivial number of POMDPs taken from a well-known third-party repository do not satisfy the accuracy condition. We propose reward-predictive state representations (R-PSRs), a generalization of PSRs which accurately models both observations and rewards, and develop value iteration for R-PSRs. We show that there is a mismatch between optimal POMDP policies and the optimal PSR policies derived from approximate rewards. On the other hand, optimal R-PSR policies perfectly match optimal POMDP policies, reconfirming R-PSRs as accurate state-less generative models of observations and rewards.","url_abs":"https://arxiv.org/abs/2106.03926v1","url_pdf":"https://arxiv.org/pdf/2106.03926v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"reconciling-rewards-with-predictive-state","repo_url":"https://github.com/abaisero/rl-rpsr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.03926","atlas_url":"https://app.syntology.ai/?focus=2106.03926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03926"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abaisero/rl-rpsr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b469c216587880cd","entry":"D","repo":"abaisero/rl-rpsr","repo_kind":"official","path":"rl_rpsr/matrices.py","file_url":"https://github.com/abaisero/rl-rpsr/blob/HEAD/rl_rpsr/matrices.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b469c216587880cd"}},{"code_sha256_prefix":"134bb68b32e10eb8","entry":"G","repo":"abaisero/rl-rpsr","repo_kind":"official","path":"rl_rpsr/matrices.py","file_url":"https://github.com/abaisero/rl-rpsr/blob/HEAD/rl_rpsr/matrices.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"134bb68b32e10eb8"}},{"code_sha256_prefix":"ce1deaebbda0c6ff","entry":"R","repo":"abaisero/rl-rpsr","repo_kind":"official","path":"rl_rpsr/matrices.py","file_url":"https://github.com/abaisero/rl-rpsr/blob/HEAD/rl_rpsr/matrices.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce1deaebbda0c6ff"}},{"code_sha256_prefix":"4cf51c7b7b8221bc","entry":"cross_sum","repo":"abaisero/rl-rpsr","repo_kind":"official","path":"rl_rpsr/linalg.py","file_url":"https://github.com/abaisero/rl-rpsr/blob/HEAD/rl_rpsr/linalg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cf51c7b7b8221bc"}},{"code_sha256_prefix":"e716845efb7aa44d","entry":"dominationCheck","repo":"abaisero/rl-rpsr","repo_kind":"official","path":"rl_rpsr/pruning.py","file_url":"https://github.com/abaisero/rl-rpsr/blob/HEAD/rl_rpsr/pruning.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e716845efb7aa44d"}},{"code_sha256_prefix":"0a49001202449c47","entry":"linearly_independent_pinv","repo":"abaisero/rl-rpsr","repo_kind":"official","path":"rl_rpsr/linalg.py","file_url":"https://github.com/abaisero/rl-rpsr/blob/HEAD/rl_rpsr/linalg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a49001202449c47"}},{"code_sha256_prefix":"b1dd92da64bdbe90","entry":"max_bigraph_distance","repo":"abaisero/rl-rpsr","repo_kind":"official","path":"rl_rpsr/linalg.py","file_url":"https://github.com/abaisero/rl-rpsr/blob/HEAD/rl_rpsr/linalg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b1dd92da64bdbe90"}},{"code_sha256_prefix":"706103e7f0c49910","entry":"purge","repo":"abaisero/rl-rpsr","repo_kind":"official","path":"rl_rpsr/pruning.py","file_url":"https://github.com/abaisero/rl-rpsr/blob/HEAD/rl_rpsr/pruning.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"706103e7f0c49910"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}