{"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/harnessing-discrete-representations-for","title":"Harnessing Discrete Representations For Continual Reinforcement Learning","arxiv_id":"2312.01203","date":"2023-12-02","proceeding":null,"authors":["Edan Meyer","Adam White","Marlos C. Machado"],"abstract":"Reinforcement learning (RL) agents make decisions using nothing but observations from the environment, and consequently, heavily rely on the representations of those observations. Though some recent breakthroughs have used vector-based categorical representations of observations, often referred to as discrete representations, there is little work explicitly assessing the significance of such a choice. In this work, we provide a thorough empirical investigation of the advantages of representing observations as vectors of categorical values within the context of reinforcement learning. We perform evaluations on world-model learning, model-free RL, and ultimately continual RL problems, where the benefits best align with the needs of the problem setting. We find that, when compared to traditional continuous representations, world models learned over discrete representations accurately model more of the world with less capacity, and that agents trained with discrete representations learn better policies with less data. In the context of continual RL, these benefits translate into faster adapting agents. Additionally, our analysis suggests that the observed performance improvements can be attributed to the information contained within the latent vectors and potentially the encoding of the discrete representation itself.","url_abs":"https://arxiv.org/abs/2312.01203v3","url_pdf":"https://arxiv.org/pdf/2312.01203v3.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":"harnessing-discrete-representations-for","repo_url":"https://github.com/ejmejm/discrete-representations-for-continual-rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.01203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01203"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/ejmejm/discrete-representations-for-continual-rl","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"70d798edc2b8bb4b","entry":"make_ae_v1","repo":"ejmejm/discrete-representations-for-continual-rl","repo_kind":"official","path":"discrete_mbrl/model_construction.py","file_url":"https://github.com/ejmejm/discrete-representations-for-continual-rl/blob/HEAD/discrete_mbrl/model_construction.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"70d798edc2b8bb4b"}},{"code_sha256_prefix":"cf53c219386e7004","entry":"make_ae_v2","repo":"ejmejm/discrete-representations-for-continual-rl","repo_kind":"official","path":"discrete_mbrl/model_construction.py","file_url":"https://github.com/ejmejm/discrete-representations-for-continual-rl/blob/HEAD/discrete_mbrl/model_construction.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cf53c219386e7004"}},{"code_sha256_prefix":"1255914a5dab35c0","entry":"make_dense_ae_v2","repo":"ejmejm/discrete-representations-for-continual-rl","repo_kind":"official","path":"discrete_mbrl/model_construction.py","file_url":"https://github.com/ejmejm/discrete-representations-for-continual-rl/blob/HEAD/discrete_mbrl/model_construction.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1255914a5dab35c0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}