{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/policy-similarity-metric","slug":"policy-similarity-metric","name":"Policy Similarity Metric","full_name":"Policy Similarity Metric","full_name_withheld":false,"description_markdown":"**Policy Similarity Metric**, or **PSM**, is a similarity metric for measuring behavioral similarity between states in reinforcement learning. It assigns high similarity to states for which the optimal policies in those states as well as in future states are similar. PSM is reward-agnostic, making it more robust for generalization compared to approaches that rely on reward information.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","paper":"/paper/contrastive-behavioral-similarity-embeddings-1","first_author":"Rishabh Agarwal","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/contrastive-behavioral-similarity-embeddings-1"},"source":{"url":"https://arxiv.org/abs/2101.05265v2","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"State Similarity Metrics","url":"/methods/category/state-similarity-metrics","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":"/paper/label-ranker-self-aware-preference-for","slug":"label-ranker-self-aware-preference-for","title":"Label Ranker: Self-Aware Preference for Classification Label Position in Visual Masked Self-Supervised Pre-Trained Model","date":"2025-03-03","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/contrastive-behavioral-similarity-embeddings-1","slug":"contrastive-behavioral-similarity-embeddings-1","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","date":"2021-01-13","arxiv_id":"2101.05265","n_code_links":1,"syntology":null}],"papers_shown":2,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":2,"with_a_code_link":2,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":2,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/dimensionality-reduction","name":"Dimensionality Reduction","papers":1},{"task":"/task/human-activity-recognition","name":"Human Activity Recognition","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/multi-label-learning","name":"Multi-Label Learning","papers":1},{"task":null,"name":"Position","papers":1},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":1},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/semantic-similarity","name":"Semantic Similarity","papers":1},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":1}],"tasks_shown":11,"n_tasks":11,"usage_by_year":[{"year":"2021","papers":1},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/policy-similarity-metric"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Policy%20Similarity%20Metric","read_at":"2026-10-05T01:00:29+00:00","query":"Policy Similarity Metric","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2101.05265","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Policy Similarity Metric' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["pathway similarity metric","Geometric Policy Composition","structural similarity metric","Metric Similarity Analysis (MSA)","Similarity Inference Metric (SIM)","Psychometric Similarity Score (PSS)","Geometric Visual Similarity Learning","Self-reflective Similarity Metric (SSM)"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"aec590c2a90ba9dd5e27b35288a810387b7bc29d73787edd049e40793bf5b45c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}