{"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/assessing-generalization-in-deep","title":"Assessing Generalization in Deep Reinforcement Learning","arxiv_id":"1810.12282","date":"2018-10-29","proceeding":"ICLR 2019 5","authors":["Charles Packer","Katelyn Gao","Jernej Kos","Philipp Krähenbühl","Vladlen Koltun","Dawn Song"],"abstract":"Deep reinforcement learning (RL) has achieved breakthrough results on many\ntasks, but agents often fail to generalize beyond the environment they were\ntrained in. As a result, deep RL algorithms that promote generalization are\nreceiving increasing attention. However, works in this area use a wide variety\nof tasks and experimental setups for evaluation. The literature lacks a\ncontrolled assessment of the merits of different generalization schemes. Our\naim is to catalyze community-wide progress on generalization in deep RL. To\nthis end, we present a benchmark and experimental protocol, and conduct a\nsystematic empirical study. Our framework contains a diverse set of\nenvironments, our methodology covers both in-distribution and\nout-of-distribution generalization, and our evaluation includes deep RL\nalgorithms that specifically tackle generalization. Our key finding is that\n`vanilla' deep RL algorithms generalize better than specialized schemes that\nwere proposed specifically to tackle generalization.","url_abs":"http://arxiv.org/abs/1810.12282v2","url_pdf":"http://arxiv.org/pdf/1810.12282v2.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":"assessing-generalization-in-deep","repo_url":"https://github.com/sunblaze-ucb/rl-generalization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.12282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12282"}},"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/sunblaze-ucb/rl-generalization","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"62d1a513f9887ba4","entry":"ActionDelayWrapper","repo":"sunblaze-ucb/rl-generalization","repo_kind":"official","path":"sunblaze_envs/wrappers.py","file_url":"https://github.com/sunblaze-ucb/rl-generalization/blob/HEAD/sunblaze_envs/wrappers.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":"62d1a513f9887ba4"}},{"code_sha256_prefix":"ca03a65a81362f81","entry":"load","repo":"sunblaze-ucb/rl-generalization","repo_kind":"official","path":"sunblaze_envs/registration.py","file_url":"https://github.com/sunblaze-ucb/rl-generalization/blob/HEAD/sunblaze_envs/registration.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":"ca03a65a81362f81"}},{"code_sha256_prefix":"8a1139c533d8f08b","entry":"make","repo":"sunblaze-ucb/rl-generalization","repo_kind":"official","path":"sunblaze_envs/registration.py","file_url":"https://github.com/sunblaze-ucb/rl-generalization/blob/HEAD/sunblaze_envs/registration.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":"8a1139c533d8f08b"}},{"code_sha256_prefix":"0c4c9f359acd3c78","entry":"register","repo":"sunblaze-ucb/rl-generalization","repo_kind":"official","path":"sunblaze_envs/registration.py","file_url":"https://github.com/sunblaze-ucb/rl-generalization/blob/HEAD/sunblaze_envs/registration.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":"0c4c9f359acd3c78"}},{"code_sha256_prefix":"67dfd3920059c1d6","entry":"uniform_exclude_inner","repo":"sunblaze-ucb/rl-generalization","repo_kind":"official","path":"sunblaze_envs/classic_control.py","file_url":"https://github.com/sunblaze-ucb/rl-generalization/blob/HEAD/sunblaze_envs/classic_control.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":"67dfd3920059c1d6"}},{"code_sha256_prefix":"ad77a1249982ee7f","entry":"wrap_environment","repo":"sunblaze-ucb/rl-generalization","repo_kind":"official","path":"sunblaze_envs/wrappers.py","file_url":"https://github.com/sunblaze-ucb/rl-generalization/blob/HEAD/sunblaze_envs/wrappers.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":"ad77a1249982ee7f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}