{"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/networkgym-reinforcement-learning","title":"NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation","arxiv_id":"2411.04138","date":"2024-10-30","proceeding":null,"authors":["Momin Haider","Ming Yin","Menglei Zhang","Arpit Gupta","Jing Zhu","Yu-Xiang Wang"],"abstract":"Mobile devices such as smartphones, laptops, and tablets can often connect to multiple access networks (e.g., Wi-Fi, LTE, and 5G) simultaneously. Recent advancements facilitate seamless integration of these connections below the transport layer, enhancing the experience for apps that lack inherent multi-path support. This optimization hinges on dynamically determining the traffic distribution across networks for each device, a process referred to as \\textit{multi-access traffic splitting}. This paper introduces \\textit{NetworkGym}, a high-fidelity network environment simulator that facilitates generating multiple network traffic flows and multi-access traffic splitting. This simulator facilitates training and evaluating different RL-based solutions for the multi-access traffic splitting problem. Our initial explorations demonstrate that the majority of existing state-of-the-art offline RL algorithms (e.g. CQL) fail to outperform certain hand-crafted heuristic policies on average. This illustrates the urgent need to evaluate offline RL algorithms against a broader range of benchmarks, rather than relying solely on popular ones such as D4RL. We also propose an extension to the TD3+BC algorithm, named Pessimistic TD3 (PTD3), and demonstrate that it outperforms many state-of-the-art offline RL algorithms. PTD3's behavioral constraint mechanism, which relies on value-function pessimism, is theoretically motivated and relatively simple to implement.","url_abs":"https://arxiv.org/abs/2411.04138v1","url_pdf":"https://arxiv.org/pdf/2411.04138v1.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":"networkgym-reinforcement-learning","repo_url":"https://github.com/hmomin/networkgym","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"d4rl","task_name":"D4RL"},{"task_slug":"management","task_name":"Management"},{"task_slug":"offline-rl","task_name":"Offline RL"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"clipped-double-q-learning","method_name":"Clipped Double Q-learning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"td3","method_name":"TD3"},{"method_slug":"target-policy-smoothing","method_name":"Target Policy Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.04138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04138"}},"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":"deterministic:regex_extraction","url":"https://github.com/tinkoff-ai/CORL","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/hmomin/networkgym","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/hmomin/CORL-compare","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":2,"ran_honours":4,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":6,"repositories":1},"found_in_text":{"samples":9,"ran":3,"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":"4e08ac58e3891cfb","entry":"compute_mean_std","repo":"hmomin/CORL-compare","repo_kind":"found_in_text","path":"algorithms/finetune/awac.py","file_url":"https://github.com/hmomin/CORL-compare/blob/HEAD/algorithms/finetune/awac.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4e08ac58e3891cfb"}},{"code_sha256_prefix":"639b4986c270df90","entry":"compute_mean_std","repo":"hmomin/CORL-compare","repo_kind":"found_in_text","path":"algorithms/finetune/iql.py","file_url":"https://github.com/hmomin/CORL-compare/blob/HEAD/algorithms/finetune/iql.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"639b4986c270df90"}},{"code_sha256_prefix":"5364f4044a619e47","entry":"Buffer","repo":"hmomin/networkgym","repo_kind":"official","path":"NetworkAgent/ptd3/agent.py","file_url":"https://github.com/hmomin/networkgym/blob/HEAD/NetworkAgent/ptd3/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5364f4044a619e47"}},{"code_sha256_prefix":"d7ae5ebb17778665","entry":"MLP","repo":"hmomin/networkgym","repo_kind":"official","path":"NetworkAgent/ptd3/agent.py","file_url":"https://github.com/hmomin/networkgym/blob/HEAD/NetworkAgent/ptd3/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d7ae5ebb17778665"}},{"code_sha256_prefix":"38e93fb6353025b8","entry":"Sherman_Morrison_inverse","repo":"hmomin/networkgym","repo_kind":"official","path":"NetworkAgent/ptd3/agent.py","file_url":"https://github.com/hmomin/networkgym/blob/HEAD/NetworkAgent/ptd3/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"38e93fb6353025b8"}},{"code_sha256_prefix":"3e80cb315de8ba69","entry":"get_num_parameters_from_matrix","repo":"hmomin/networkgym","repo_kind":"official","path":"NetworkAgent/ptd3/agent.py","file_url":"https://github.com/hmomin/networkgym/blob/HEAD/NetworkAgent/ptd3/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e80cb315de8ba69"}},{"code_sha256_prefix":"ba80f9ff81b1de5f","entry":"normalize_states","repo":"hmomin/CORL-compare","repo_kind":"found_in_text","path":"algorithms/finetune/awac.py","file_url":"https://github.com/hmomin/CORL-compare/blob/HEAD/algorithms/finetune/awac.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"code_sha256_prefix":"835cbe687de8fb40","entry":"safe_concat","repo":"hmomin/networkgym","repo_kind":"official","path":"NetworkAgent/ptd3/agent.py","file_url":"https://github.com/hmomin/networkgym/blob/HEAD/NetworkAgent/ptd3/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"835cbe687de8fb40"}},{"code_sha256_prefix":"26f75cae6942c75c","entry":"safe_stack","repo":"hmomin/networkgym","repo_kind":"official","path":"NetworkAgent/ptd3/agent.py","file_url":"https://github.com/hmomin/networkgym/blob/HEAD/NetworkAgent/ptd3/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"26f75cae6942c75c"}},{"code_sha256_prefix":"9f18e9c6c8c3eb47","entry":"CombinedBuffer","repo":"hmomin/networkgym","repo_kind":"official","path":"NetworkAgent/ptd3/agent.py","file_url":"https://github.com/hmomin/networkgym/blob/HEAD/NetworkAgent/ptd3/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f18e9c6c8c3eb47"}},{"code_sha256_prefix":"b1d7b6c14279e8ed","entry":"OfflineEnv","repo":"hmomin/networkgym","repo_kind":"official","path":"NetworkAgent/ptd3/agent.py","file_url":"https://github.com/hmomin/networkgym/blob/HEAD/NetworkAgent/ptd3/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b1d7b6c14279e8ed"}},{"code_sha256_prefix":"3a9e7d766c9d5bef","entry":"PessimisticTD3","repo":"hmomin/networkgym","repo_kind":"official","path":"NetworkAgent/ptd3/agent.py","file_url":"https://github.com/hmomin/networkgym/blob/HEAD/NetworkAgent/ptd3/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3a9e7d766c9d5bef"}},{"code_sha256_prefix":"e482b76be0b40fe2","entry":"get_average_scores","repo":"hmomin/CORL-compare","repo_kind":"found_in_text","path":"results/get_finetune_tables_and_plots.py","file_url":"https://github.com/hmomin/CORL-compare/blob/HEAD/results/get_finetune_tables_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e482b76be0b40fe2"}},{"code_sha256_prefix":"8cee6cb43695037e","entry":"get_last_scores","repo":"hmomin/CORL-compare","repo_kind":"found_in_text","path":"results/get_finetune_tables_and_plots.py","file_url":"https://github.com/hmomin/CORL-compare/blob/HEAD/results/get_finetune_tables_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8cee6cb43695037e"}},{"code_sha256_prefix":"b55784199eb66664","entry":"get_max_scores","repo":"hmomin/CORL-compare","repo_kind":"found_in_text","path":"results/get_finetune_tables_and_plots.py","file_url":"https://github.com/hmomin/CORL-compare/blob/HEAD/results/get_finetune_tables_and_plots.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b55784199eb66664"}},{"code_sha256_prefix":"80f4da28d1c7ef4f","entry":"wrap_env","repo":"hmomin/CORL-compare","repo_kind":"found_in_text","path":"algorithms/finetune/awac.py","file_url":"https://github.com/hmomin/CORL-compare/blob/HEAD/algorithms/finetune/awac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"80f4da28d1c7ef4f"}},{"code_sha256_prefix":"4dd56ecf0f797666","entry":"wrap_env","repo":"hmomin/CORL-compare","repo_kind":"found_in_text","path":"algorithms/finetune/cal_ql.py","file_url":"https://github.com/hmomin/CORL-compare/blob/HEAD/algorithms/finetune/cal_ql.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4dd56ecf0f797666"}},{"code_sha256_prefix":"a8341f5e34d50ae6","entry":"wrap_env","repo":"hmomin/CORL-compare","repo_kind":"found_in_text","path":"algorithms/finetune/iql.py","file_url":"https://github.com/hmomin/CORL-compare/blob/HEAD/algorithms/finetune/iql.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a8341f5e34d50ae6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}