{"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/integrating-deep-reinforcement-learning-with","title":"Integrating Deep Reinforcement Learning with Model-based Path Planners for Automated Driving","arxiv_id":"2002.00434","date":"2020-02-02","proceeding":null,"authors":["Ekim Yurtsever","Linda Capito","Keith Redmill","Umit Ozguner"],"abstract":"Automated driving in urban settings is challenging. Human participant behavior is difficult to model, and conventional, rule-based Automated Driving Systems (ADSs) tend to fail when they face unmodeled dynamics. On the other hand, the more recent, end-to-end Deep Reinforcement Learning (DRL) based model-free ADSs have shown promising results. However, pure learning-based approaches lack the hard-coded safety measures of model-based controllers. Here we propose a hybrid approach for integrating a path planning pipe into a vision based DRL framework to alleviate the shortcomings of both worlds. In summary, the DRL agent is trained to follow the path planner's waypoints as close as possible. The agent learns this policy by interacting with the environment. The reward function contains two major terms: the penalty of straying away from the path planner and the penalty of having a collision. The latter has precedence in the form of having a significantly greater numerical value. Experimental results show that the proposed method can plan its path and navigate between randomly chosen origin-destination points in CARLA, a dynamic urban simulation environment. Our code is open-source and available online.","url_abs":"https://arxiv.org/abs/2002.00434v2","url_pdf":"https://arxiv.org/pdf/2002.00434v2.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":"integrating-deep-reinforcement-learning-with","repo_url":"https://github.com/Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving","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":"navigate","task_name":"Navigate"},{"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":"carla","method_name":"CARLA"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.00434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.00434"}},"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/Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"ccc25780948874cb","entry":"clamp","repo":"Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving","repo_kind":"official","path":"hybrid-rl/sources/carla.py","file_url":"https://github.com/Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving/blob/HEAD/hybrid-rl/sources/carla.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ccc25780948874cb"}},{"code_sha256_prefix":"83a20a9bd5e1d806","entry":"get_hparams","repo":"Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving","repo_kind":"official","path":"hybrid-rl/sources/common.py","file_url":"https://github.com/Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving/blob/HEAD/hybrid-rl/sources/common.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":"83a20a9bd5e1d806"}},{"code_sha256_prefix":"7c356e828384588c","entry":"model_base_64x3_CNN","repo":"Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving","repo_kind":"official","path":"hybrid-rl/sources/models.py","file_url":"https://github.com/Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving/blob/HEAD/hybrid-rl/sources/models.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":"7c356e828384588c"}},{"code_sha256_prefix":"3dea59107defb78a","entry":"model_base_Xception","repo":"Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving","repo_kind":"official","path":"hybrid-rl/sources/models.py","file_url":"https://github.com/Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving/blob/HEAD/hybrid-rl/sources/models.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":"3dea59107defb78a"}},{"code_sha256_prefix":"1ec120f59bec8fb2","entry":"model_base_test_CNN","repo":"Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving","repo_kind":"official","path":"hybrid-rl/sources/models.py","file_url":"https://github.com/Ekim-Yurtsever/Hybrid-DeepRL-Automated-Driving/blob/HEAD/hybrid-rl/sources/models.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":"1ec120f59bec8fb2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}