{"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/real-time-reinforcement-learning","title":"Real-Time Reinforcement Learning","arxiv_id":"1911.04448","date":"2019-11-11","proceeding":"NeurIPS 2019 12","authors":["Simon Ramstedt","Christopher Pal"],"abstract":"Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used in a way that wrongfully assumes that the state of an agent's environment does not change during action selection. As RL systems based on MDPs begin to find application in real-world safety critical situations, this mismatch between the assumptions underlying classical MDPs and the reality of real-time computation may lead to undesirable outcomes. In this paper, we introduce a new framework, in which states and actions evolve simultaneously and show how it is related to the classical MDP formulation. We analyze existing algorithms under the new real-time formulation and show why they are suboptimal when used in real-time. We then use those insights to create a new algorithm Real-Time Actor-Critic (RTAC) that outperforms the existing state-of-the-art continuous control algorithm Soft Actor-Critic both in real-time and non-real-time settings. Code and videos can be found at https://github.com/rmst/rtrl.","url_abs":"https://arxiv.org/abs/1911.04448v4","url_pdf":"https://arxiv.org/pdf/1911.04448v4.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":"real-time-reinforcement-learning","repo_url":"https://github.com/rmst/rtrl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"real-time-reinforcement-learning","repo_url":"https://github.com/elementai/avenue","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"real-time-reinforcement-learning","repo_url":"https://github.com/yannbouteiller/gym-airsimdroneracinglab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.04448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.04448"}},"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/elementai/avenue","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yannbouteiller/gym-airsimdroneracinglab","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rmst/rtrl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":16},"by_repo_kind":{"official":{"samples":12,"ran":0,"repositories":2},"listed":{"samples":4,"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":"4f1fcee7a0959171","entry":"basis_oriented_quaternion","repo":"yannbouteiller/gym-airsimdroneracinglab","repo_kind":"listed","path":"gym_game_of_drones/envs/multi_agent/gym_airsimdroneracinglab/airsimdroneracinglab_env.py","file_url":"https://github.com/yannbouteiller/gym-airsimdroneracinglab/blob/HEAD/gym_game_of_drones/envs/multi_agent/gym_airsimdroneracinglab/airsimdroneracinglab_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":"4f1fcee7a0959171"}},{"code_sha256_prefix":"37983d1795ec599f","entry":"collate","repo":"rmst/rtrl","repo_kind":"official","path":"rtrl/util.py","file_url":"https://github.com/rmst/rtrl/blob/HEAD/rtrl/util.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":"37983d1795ec599f"}},{"code_sha256_prefix":"9e6f271628db1153","entry":"compute_assed_id","repo":"elementai/avenue","repo_kind":"official","path":"avenue/util.py","file_url":"https://github.com/elementai/avenue/blob/HEAD/avenue/util.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":"9e6f271628db1153"}},{"code_sha256_prefix":"3898cde4a2e9842f","entry":"compute_asset_path","repo":"elementai/avenue","repo_kind":"official","path":"avenue/util.py","file_url":"https://github.com/elementai/avenue/blob/HEAD/avenue/util.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":"3898cde4a2e9842f"}},{"code_sha256_prefix":"38e629a2f8bc42de","entry":"concat_spaces_from_dict","repo":"elementai/avenue","repo_kind":"official","path":"avenue/wrappers.py","file_url":"https://github.com/elementai/avenue/blob/HEAD/avenue/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":"38e629a2f8bc42de"}},{"code_sha256_prefix":"f3ed23b35cd6dba4","entry":"copy_shared","repo":"rmst/rtrl","repo_kind":"official","path":"rtrl/nn.py","file_url":"https://github.com/rmst/rtrl/blob/HEAD/rtrl/nn.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":"f3ed23b35cd6dba4"}},{"code_sha256_prefix":"c64381a3a6c81fd5","entry":"dqn_conv","repo":"rmst/rtrl","repo_kind":"official","path":"rtrl/nn.py","file_url":"https://github.com/rmst/rtrl/blob/HEAD/rtrl/nn.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":"c64381a3a6c81fd5"}},{"code_sha256_prefix":"d4a1d5bcb45f2a7b","entry":"float64_to_float32","repo":"rmst/rtrl","repo_kind":"official","path":"rtrl/wrappers.py","file_url":"https://github.com/rmst/rtrl/blob/HEAD/rtrl/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":"d4a1d5bcb45f2a7b"}},{"code_sha256_prefix":"49fd27673ae96565","entry":"get_wrapper_by_class","repo":"rmst/rtrl","repo_kind":"official","path":"rtrl/wrappers.py","file_url":"https://github.com/rmst/rtrl/blob/HEAD/rtrl/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":"49fd27673ae96565"}},{"code_sha256_prefix":"bbaf3f539ccf9404","entry":"min_max_norm","repo":"elementai/avenue","repo_kind":"official","path":"avenue/util.py","file_url":"https://github.com/elementai/avenue/blob/HEAD/avenue/util.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":"bbaf3f539ccf9404"}},{"code_sha256_prefix":"064f68f60a5e4279","entry":"no_grad","repo":"rmst/rtrl","repo_kind":"official","path":"rtrl/nn.py","file_url":"https://github.com/rmst/rtrl/blob/HEAD/rtrl/nn.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":"064f68f60a5e4279"}},{"code_sha256_prefix":"c0504dae0e2af9cc","entry":"partition","repo":"rmst/rtrl","repo_kind":"official","path":"rtrl/util.py","file_url":"https://github.com/rmst/rtrl/blob/HEAD/rtrl/util.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":"c0504dae0e2af9cc"}},{"code_sha256_prefix":"445cd0db640c75dc","entry":"quaternion_to_euler","repo":"yannbouteiller/gym-airsimdroneracinglab","repo_kind":"listed","path":"gym_game_of_drones/dataset_collector_game.py","file_url":"https://github.com/yannbouteiller/gym-airsimdroneracinglab/blob/HEAD/gym_game_of_drones/dataset_collector_game.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":"445cd0db640c75dc"}},{"code_sha256_prefix":"b4dafd10c6a29ce4","entry":"quaternion_to_yaw","repo":"yannbouteiller/gym-airsimdroneracinglab","repo_kind":"listed","path":"gym_game_of_drones/envs/multi_agent/gym_airsimdroneracinglab/rewardfunction.py","file_url":"https://github.com/yannbouteiller/gym-airsimdroneracinglab/blob/HEAD/gym_game_of_drones/envs/multi_agent/gym_airsimdroneracinglab/rewardfunction.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":"b4dafd10c6a29ce4"}},{"code_sha256_prefix":"fa1168e9585a6ae1","entry":"quaternions_to_gate_yaw_cos","repo":"yannbouteiller/gym-airsimdroneracinglab","repo_kind":"listed","path":"gym_game_of_drones/envs/multi_agent/gym_airsimdroneracinglab/rewardfunction.py","file_url":"https://github.com/yannbouteiller/gym-airsimdroneracinglab/blob/HEAD/gym_game_of_drones/envs/multi_agent/gym_airsimdroneracinglab/rewardfunction.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":"fa1168e9585a6ae1"}},{"code_sha256_prefix":"592c3fc322538b71","entry":"shallow_copy","repo":"rmst/rtrl","repo_kind":"official","path":"rtrl/util.py","file_url":"https://github.com/rmst/rtrl/blob/HEAD/rtrl/util.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":"592c3fc322538b71"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}