{"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/deep-neuroevolution-of-recurrent-and-discrete","title":"Deep Neuroevolution of Recurrent and Discrete World Models","arxiv_id":"1906.08857","date":"2019-04-28","proceeding":null,"authors":["Sebastian Risi","Kenneth O. Stanley"],"abstract":"Neural architectures inspired by our own human cognitive system, such as the recently introduced world models, have been shown to outperform traditional deep reinforcement learning (RL) methods in a variety of different domains. Instead of the relatively simple architectures employed in most RL experiments, world models rely on multiple different neural components that are responsible for visual information processing, memory, and decision-making. However, so far the components of these models have to be trained separately and through a variety of specialized training methods. This paper demonstrates the surprising finding that models with the same precise parts can be instead efficiently trained end-to-end through a genetic algorithm (GA), reaching a comparable performance to the original world model by solving a challenging car racing task. An analysis of the evolved visual and memory system indicates that they include a similar effective representation to the system trained through gradient descent. Additionally, in contrast to gradient descent methods that struggle with discrete variables, GAs also work directly with such representations, opening up opportunities for classical planning in latent space. This paper adds additional evidence on the effectiveness of deep neuroevolution for tasks that require the intricate orchestration of multiple components in complex heterogeneous architectures.","url_abs":"https://arxiv.org/abs/1906.08857v1","url_pdf":"https://arxiv.org/pdf/1906.08857v1.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":"deep-neuroevolution-of-recurrent-and-discrete","repo_url":"https://github.com/sebastianrisi/ga-world-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-neuroevolution-of-recurrent-and-discrete","repo_url":"https://github.com/plaffa/discrete-world-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-neuroevolution-of-recurrent-and-discrete","repo_url":"https://github.com/samuel500/World-Models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-neuroevolution-of-recurrent-and-discrete","repo_url":"https://github.com/uber-research/ga-world-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"car-racing","task_name":"Car Racing"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1906.08857","atlas_url":"https://app.syntology.ai/?focus=1906.08857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08857"}},"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/samuel500/World-Models","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sebastianrisi/ga-world-models","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uber-research/ga-world-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/plaffa/discrete-world-models","reach":{"status":"ok"}}],"summary":{"ran_fixture":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"4673c35a65217500","entry":"gmm_loss","repo":"uber-research/ga-world-models","repo_kind":"listed","path":"models/mdrnn.py","file_url":"https://github.com/uber-research/ga-world-models/blob/HEAD/models/mdrnn.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4673c35a65217500"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}