{"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/learning-to-drive-in-a-day","title":"Learning to Drive in a Day","arxiv_id":"1807.00412","date":"2018-07-01","proceeding":null,"authors":["Alex Kendall","Jeffrey Hawke","David Janz","Przemyslaw Mazur","Daniele Reda","John-Mark Allen","Vinh-Dieu Lam","Alex Bewley","Amar Shah"],"abstract":"We demonstrate the first application of deep reinforcement learning to\nautonomous driving. From randomly initialised parameters, our model is able to\nlearn a policy for lane following in a handful of training episodes using a\nsingle monocular image as input. We provide a general and easy to obtain\nreward: the distance travelled by the vehicle without the safety driver taking\ncontrol. We use a continuous, model-free deep reinforcement learning algorithm,\nwith all exploration and optimisation performed on-vehicle. This demonstrates a\nnew framework for autonomous driving which moves away from reliance on defined\nlogical rules, mapping, and direct supervision. We discuss the challenges and\nopportunities to scale this approach to a broader range of autonomous driving\ntasks.","url_abs":"http://arxiv.org/abs/1807.00412v2","url_pdf":"http://arxiv.org/pdf/1807.00412v2.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":"learning-to-drive-in-a-day","repo_url":"https://github.com/B-C-WANG/ReinforcementLearningInAutoPilot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-drive-in-a-day","repo_url":"https://github.com/ZexinLi0w0/R3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-drive-in-a-day","repo_url":"https://github.com/ankur-rc/autodrive_ddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"learning-to-drive-in-a-day","repo_url":"https://github.com/araffin/learning-to-drive-in-5-minutes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-drive-in-a-day","repo_url":"https://github.com/bitsauce/Carla-ppo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-drive-in-a-day","repo_url":"https://github.com/bryonkucharski/Learning-to-Drive-with-Reinforcement-Learning-and-Variational-Autoencoders","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-drive-in-a-day","repo_url":"https://github.com/bryonkucharski/learning-to-drive-in-a-day-reproduction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-drive-in-a-day","repo_url":"https://github.com/nautilusPrime/autodrive_ddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"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)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.00412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.00412"}},"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/B-C-WANG/ReinforcementLearningInAutoPilot","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nautilusPrime/autodrive_ddpg","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZexinLi0w0/R3","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/araffin/learning-to-drive-in-5-minutes","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bryonkucharski/Learning-to-Drive-with-Reinforcement-Learning-and-Variational-Autoencoders","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ankur-rc/autodrive_ddpg","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bitsauce/Carla-ppo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bryonkucharski/learning-to-drive-in-a-day-reproduction","reach":{"status":"ok"}}],"summary":{"unverified":22},"by_repo_kind":{"listed":{"samples":22,"ran":0,"repositories":3}},"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":"476e97084d993bdd","entry":"EuclideanDistanceOfTwoArray","repo":"B-C-WANG/ReinforcementLearningInAutoPilot","repo_kind":"listed","path":"src/common/Math.py","file_url":"https://github.com/B-C-WANG/ReinforcementLearningInAutoPilot/blob/HEAD/src/common/Math.py","link_basis":"harvester_set","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":"476e97084d993bdd"}},{"code_sha256_prefix":"9cd3951cc9690df9","entry":"PointEuclideanDistance","repo":"B-C-WANG/ReinforcementLearningInAutoPilot","repo_kind":"listed","path":"src/common/Math.py","file_url":"https://github.com/B-C-WANG/ReinforcementLearningInAutoPilot/blob/HEAD/src/common/Math.py","link_basis":"harvester_set","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":"9cd3951cc9690df9"}},{"code_sha256_prefix":"3be08c616e19292b","entry":"PointManhattenDistance","repo":"B-C-WANG/ReinforcementLearningInAutoPilot","repo_kind":"listed","path":"src/common/Math.py","file_url":"https://github.com/B-C-WANG/ReinforcementLearningInAutoPilot/blob/HEAD/src/common/Math.py","link_basis":"harvester_set","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":"3be08c616e19292b"}},{"code_sha256_prefix":"a7512ef5c4442dcb","entry":"as_scalar","repo":"araffin/learning-to-drive-in-5-minutes","repo_kind":"listed","path":"algos/custom_ddpg.py","file_url":"https://github.com/araffin/learning-to-drive-in-5-minutes/blob/HEAD/algos/custom_ddpg.py","link_basis":"harvester_set","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":"a7512ef5c4442dcb"}},{"code_sha256_prefix":"cc9ec10cd6121f37","entry":"bce_loss","repo":"bitsauce/Carla-ppo","repo_kind":"listed","path":"vae/models.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/vae/models.py","link_basis":"harvester_set","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":"cc9ec10cd6121f37"}},{"code_sha256_prefix":"7e4e11e5573d79e3","entry":"bce_loss_v2","repo":"bitsauce/Carla-ppo","repo_kind":"listed","path":"vae/models.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/vae/models.py","link_basis":"harvester_set","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":"7e4e11e5573d79e3"}},{"code_sha256_prefix":"52cd76f959b4b587","entry":"build_mlp","repo":"bitsauce/Carla-ppo","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/utils.py","link_basis":"harvester_set","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":"52cd76f959b4b587"}},{"code_sha256_prefix":"9aa5b6ae6396d065","entry":"colored_reward","repo":"B-C-WANG/ReinforcementLearningInAutoPilot","repo_kind":"listed","path":"src/ReinforcementLearning/Modules/utils.py","file_url":"https://github.com/B-C-WANG/ReinforcementLearningInAutoPilot/blob/HEAD/src/ReinforcementLearning/Modules/utils.py","link_basis":"harvester_set","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":"9aa5b6ae6396d065"}},{"code_sha256_prefix":"7a3cb3b54406c5a5","entry":"control","repo":"araffin/learning-to-drive-in-5-minutes","repo_kind":"listed","path":"teleop/teleop_client.py","file_url":"https://github.com/araffin/learning-to-drive-in-5-minutes/blob/HEAD/teleop/teleop_client.py","link_basis":"harvester_set","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":"7a3cb3b54406c5a5"}},{"code_sha256_prefix":"336792a8829b2c8a","entry":"conv_to_fc","repo":"araffin/learning-to-drive-in-5-minutes","repo_kind":"listed","path":"vae/model.py","file_url":"https://github.com/araffin/learning-to-drive-in-5-minutes/blob/HEAD/vae/model.py","link_basis":"harvester_set","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":"336792a8829b2c8a"}},{"code_sha256_prefix":"105d78f10aeaf14b","entry":"create_counter_variable","repo":"bitsauce/Carla-ppo","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/utils.py","link_basis":"harvester_set","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":"105d78f10aeaf14b"}},{"code_sha256_prefix":"6170c85b07d9ae9d","entry":"create_mean_metrics_from_dict","repo":"bitsauce/Carla-ppo","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/utils.py","link_basis":"harvester_set","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":"6170c85b07d9ae9d"}},{"code_sha256_prefix":"364e7223f4d9779a","entry":"create_reward_fn","repo":"bitsauce/Carla-ppo","repo_kind":"listed","path":"reward_functions.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/reward_functions.py","link_basis":"harvester_set","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":"364e7223f4d9779a"}},{"code_sha256_prefix":"c58cb9a54a9aab94","entry":"kl_divergence","repo":"bitsauce/Carla-ppo","repo_kind":"listed","path":"vae/models.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/vae/models.py","link_basis":"harvester_set","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":"c58cb9a54a9aab94"}},{"code_sha256_prefix":"e050c4b636eae696","entry":"preprocess_frame","repo":"bitsauce/Carla-ppo","repo_kind":"listed","path":"vae_common.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/vae_common.py","link_basis":"harvester_set","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":"e050c4b636eae696"}},{"code_sha256_prefix":"01fbad3c85943e3f","entry":"record","repo":"B-C-WANG/ReinforcementLearningInAutoPilot","repo_kind":"listed","path":"src/ReinforcementLearning/Modules/utils.py","file_url":"https://github.com/B-C-WANG/ReinforcementLearningInAutoPilot/blob/HEAD/src/ReinforcementLearning/Modules/utils.py","link_basis":"harvester_set","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":"01fbad3c85943e3f"}},{"code_sha256_prefix":"c5aeb2054758da8f","entry":"reflection_matrix","repo":"B-C-WANG/ReinforcementLearningInAutoPilot","repo_kind":"listed","path":"src/thirdParty/transformations.py","file_url":"https://github.com/B-C-WANG/ReinforcementLearningInAutoPilot/blob/HEAD/src/thirdParty/transformations.py","link_basis":"harvester_set","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":"c5aeb2054758da8f"}},{"code_sha256_prefix":"41ef4fefb86dd6fa","entry":"replace_float_notation","repo":"araffin/learning-to-drive-in-5-minutes","repo_kind":"listed","path":"donkey_gym/core/tcp_server.py","file_url":"https://github.com/araffin/learning-to-drive-in-5-minutes/blob/HEAD/donkey_gym/core/tcp_server.py","link_basis":"harvester_set","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":"41ef4fefb86dd6fa"}},{"code_sha256_prefix":"810da5dae21567b6","entry":"reward_fn","repo":"bitsauce/Carla-ppo","repo_kind":"listed","path":"CarlaEnv/carla_lap_env.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/CarlaEnv/carla_lap_env.py","link_basis":"harvester_set","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":"810da5dae21567b6"}},{"code_sha256_prefix":"e0244485db7fab7f","entry":"reward_kendall","repo":"bitsauce/Carla-ppo","repo_kind":"listed","path":"reward_functions.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/reward_functions.py","link_basis":"harvester_set","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":"e0244485db7fab7f"}},{"code_sha256_prefix":"77cb383b0cd2a54e","entry":"translation_from_matrix","repo":"B-C-WANG/ReinforcementLearningInAutoPilot","repo_kind":"listed","path":"src/thirdParty/transformations.py","file_url":"https://github.com/B-C-WANG/ReinforcementLearningInAutoPilot/blob/HEAD/src/thirdParty/transformations.py","link_basis":"harvester_set","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":"77cb383b0cd2a54e"}},{"code_sha256_prefix":"edeb1406911ce025","entry":"translation_matrix","repo":"B-C-WANG/ReinforcementLearningInAutoPilot","repo_kind":"listed","path":"src/thirdParty/transformations.py","file_url":"https://github.com/B-C-WANG/ReinforcementLearningInAutoPilot/blob/HEAD/src/thirdParty/transformations.py","link_basis":"harvester_set","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":"edeb1406911ce025"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}