{"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/intelligent-switching-for-reset-free-rl","title":"Intelligent Switching for Reset-Free RL","arxiv_id":"2405.01684","date":"2024-05-02","proceeding":null,"authors":["Darshan Patil","Janarthanan Rajendran","Glen Berseth","Sarath Chandar"],"abstract":"In the real world, the strong episode resetting mechanisms that are needed to train agents in simulation are unavailable. The \\textit{resetting} assumption limits the potential of reinforcement learning in the real world, as providing resets to an agent usually requires the creation of additional handcrafted mechanisms or human interventions. Recent work aims to train agents (\\textit{forward}) with learned resets by constructing a second (\\textit{backward}) agent that returns the forward agent to the initial state. We find that the termination and timing of the transitions between these two agents are crucial for algorithm success. With this in mind, we create a new algorithm, Reset Free RL with Intelligently Switching Controller (RISC) which intelligently switches between the two agents based on the agent's confidence in achieving its current goal. Our new method achieves state-of-the-art performance on several challenging environments for reset-free RL.","url_abs":"https://arxiv.org/abs/2405.01684v1","url_pdf":"https://arxiv.org/pdf/2405.01684v1.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":"intelligent-switching-for-reset-free-rl","repo_url":"https://github.com/chandar-lab/risc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.01684","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01684"}},"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/chandar-lab/risc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"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":"2b1516735f581e2d","entry":"composite_logger_hack","repo":"chandar-lab/risc","repo_kind":"official","path":"risc/wandb_logger.py","file_url":"https://github.com/chandar-lab/risc/blob/HEAD/risc/wandb_logger.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b1516735f581e2d"}},{"code_sha256_prefix":"6068902c5debd8c4","entry":"config_fn_decorator","repo":"chandar-lab/risc","repo_kind":"official","path":"risc/config_generator.py","file_url":"https://github.com/chandar-lab/risc/blob/HEAD/risc/config_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6068902c5debd8c4"}},{"code_sha256_prefix":"f3504c35509ab24a","entry":"convert_to_gc_obs","repo":"chandar-lab/risc","repo_kind":"official","path":"risc/envs/earl.py","file_url":"https://github.com/chandar-lab/risc/blob/HEAD/risc/envs/earl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3504c35509ab24a"}},{"code_sha256_prefix":"d06204e7d6ea3fe3","entry":"generate_dqn_agent_config","repo":"chandar-lab/risc","repo_kind":"official","path":"risc/config_generator.py","file_url":"https://github.com/chandar-lab/risc/blob/HEAD/risc/config_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d06204e7d6ea3fe3"}},{"code_sha256_prefix":"73036d9dc0b4f111","entry":"generate_sac_agent_config","repo":"chandar-lab/risc","repo_kind":"official","path":"risc/config_generator.py","file_url":"https://github.com/chandar-lab/risc/blob/HEAD/risc/config_generator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73036d9dc0b4f111"}},{"code_sha256_prefix":"dcb668045e7d2275","entry":"oracle_policy","repo":"chandar-lab/risc","repo_kind":"official","path":"risc/agents/dqn.py","file_url":"https://github.com/chandar-lab/risc/blob/HEAD/risc/agents/dqn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dcb668045e7d2275"}},{"code_sha256_prefix":"00775fcf95f75ef4","entry":"oracle_q_value","repo":"chandar-lab/risc","repo_kind":"official","path":"risc/agents/dqn.py","file_url":"https://github.com/chandar-lab/risc/blob/HEAD/risc/agents/dqn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00775fcf95f75ef4"}},{"code_sha256_prefix":"9f33cc58c2049c9d","entry":"process_demos","repo":"chandar-lab/risc","repo_kind":"official","path":"risc/envs/earl.py","file_url":"https://github.com/chandar-lab/risc/blob/HEAD/risc/envs/earl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f33cc58c2049c9d"}},{"code_sha256_prefix":"e6e7de2c526523dc","entry":"replace_goal_fn","repo":"chandar-lab/risc","repo_kind":"official","path":"risc/envs/earl.py","file_url":"https://github.com/chandar-lab/risc/blob/HEAD/risc/envs/earl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e6e7de2c526523dc"}},{"code_sha256_prefix":"ef33a904f943c1cc","entry":"create_every_eval_env","repo":"chandar-lab/risc","repo_kind":"official","path":"risc/envs/minigrid_rf.py","file_url":"https://github.com/chandar-lab/risc/blob/HEAD/risc/envs/minigrid_rf.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":"ef33a904f943c1cc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}