{"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/reverse-forward-curriculum-learning-for","title":"Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning","arxiv_id":"2405.03379","date":"2024-05-06","proceeding":null,"authors":["Stone Tao","Arth Shukla","Tse-kai Chan","Hao Su"],"abstract":"Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes augmenting RL with offline data demonstrating desired tasks, but past work often require a lot of high-quality demonstration data that is difficult to obtain, especially for domains such as robotics. Our approach consists of a reverse curriculum followed by a forward curriculum. Unique to our approach compared to past work is the ability to efficiently leverage more than one demonstration via a per-demonstration reverse curriculum generated via state resets. The result of our reverse curriculum is an initial policy that performs well on a narrow initial state distribution and helps overcome difficult exploration problems. A forward curriculum is then used to accelerate the training of the initial policy to perform well on the full initial state distribution of the task and improve demonstration and sample efficiency. We show how the combination of a reverse curriculum and forward curriculum in our method, RFCL, enables significant improvements in demonstration and sample efficiency compared against various state-of-the-art learning-from-demonstration baselines, even solving previously unsolvable tasks that require high precision and control.","url_abs":"https://arxiv.org/abs/2405.03379v1","url_pdf":"https://arxiv.org/pdf/2405.03379v1.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":"reverse-forward-curriculum-learning-for","repo_url":"https://github.com/stonet2000/rfcl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.03379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03379"}},"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/stonet2000/rfcl","reach":{"status":"ok"}}],"summary":{"ran":7},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":7,"samples":[{"code_sha256_prefix":"effb7e693918b58b","entry":"activation_to_fn","repo":"stonet2000/rfcl","repo_kind":"official","path":"rfcl/models/builder.py","file_url":"https://github.com/stonet2000/rfcl/blob/HEAD/rfcl/models/builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"effb7e693918b58b"}},{"code_sha256_prefix":"7e36f1c357c4618d","entry":"colorize","repo":"stonet2000/rfcl","repo_kind":"official","path":"rfcl/logger/logger.py","file_url":"https://github.com/stonet2000/rfcl/blob/HEAD/rfcl/logger/logger.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7e36f1c357c4618d"}},{"code_sha256_prefix":"d8302176def1e542","entry":"default_init","repo":"stonet2000/rfcl","repo_kind":"official","path":"rfcl/models/mlp.py","file_url":"https://github.com/stonet2000/rfcl/blob/HEAD/rfcl/models/mlp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d8302176def1e542"}},{"code_sha256_prefix":"32b82cb936cbd54d","entry":"default_init","repo":"stonet2000/rfcl","repo_kind":"official","path":"rfcl/agents/sac/networks.py","file_url":"https://github.com/stonet2000/rfcl/blob/HEAD/rfcl/agents/sac/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32b82cb936cbd54d"}},{"code_sha256_prefix":"4a540e170b5725f8","entry":"is_discrete_action_space","repo":"stonet2000/rfcl","repo_kind":"official","path":"rfcl/utils/spaces.py","file_url":"https://github.com/stonet2000/rfcl/blob/HEAD/rfcl/utils/spaces.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4a540e170b5725f8"}},{"code_sha256_prefix":"286a32d712c1a70d","entry":"load_json","repo":"stonet2000/rfcl","repo_kind":"official","path":"rfcl/utils/io_utils.py","file_url":"https://github.com/stonet2000/rfcl/blob/HEAD/rfcl/utils/io_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"286a32d712c1a70d"}},{"code_sha256_prefix":"ed51992b2a581ba6","entry":"parse_cfg","repo":"stonet2000/rfcl","repo_kind":"official","path":"rfcl/utils/parse.py","file_url":"https://github.com/stonet2000/rfcl/blob/HEAD/rfcl/utils/parse.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ed51992b2a581ba6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}