{"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/pebble-feedback-efficient-interactive","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","arxiv_id":"2106.05091","date":"2021-06-09","proceeding":null,"authors":["Kimin Lee","Laura Smith","Pieter Abbeel"],"abstract":"Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow practitioners to instead interactively teach agents through tailored feedback; however, such approaches have been challenging to scale since human feedback is very expensive. In this work, we aim to make this process more sample- and feedback-efficient. We present an off-policy, interactive RL algorithm that capitalizes on the strengths of both feedback and off-policy learning. Specifically, we learn a reward model by actively querying a teacher's preferences between two clips of behavior and use it to train an agent. To enable off-policy learning, we relabel all the agent's past experience when its reward model changes. We additionally show that pre-training our agents with unsupervised exploration substantially increases the mileage of its queries. We demonstrate that our approach is capable of learning tasks of higher complexity than previously considered by human-in-the-loop methods, including a variety of locomotion and robotic manipulation skills. We also show that our method is able to utilize real-time human feedback to effectively prevent reward exploitation and learn new behaviors that are difficult to specify with standard reward functions.","url_abs":"https://arxiv.org/abs/2106.05091v1","url_pdf":"https://arxiv.org/pdf/2106.05091v1.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":"pebble-feedback-efficient-interactive","repo_url":"https://github.com/rll-research/bpref","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"pebble-feedback-efficient-interactive","repo_url":"https://github.com/pokaxpoka/b_pref","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.05091","atlas_url":"https://app.syntology.ai/?focus=2106.05091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05091"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/rll-research/bpref","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pokaxpoka/b_pref","reach":null}],"summary":{"ran_draft_wrong":2,"ran":1,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"repositories":1},"listed":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"c30edaf748298765","entry":"KCenterGreedy","repo":"pokaxpoka/b_pref","repo_kind":"listed","path":"reward_model.py","file_url":"https://github.com/pokaxpoka/b_pref/blob/HEAD/reward_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c30edaf748298765"}},{"code_sha256_prefix":"7317e4f9684221bb","entry":"RewardModel","repo":"pokaxpoka/b_pref","repo_kind":"listed","path":"reward_model.py","file_url":"https://github.com/pokaxpoka/b_pref/blob/HEAD/reward_model.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":"7317e4f9684221bb"}},{"code_sha256_prefix":"9d7e96fcfe3ff0f4","entry":"compute_smallest_dist","repo":"pokaxpoka/b_pref","repo_kind":"listed","path":"reward_model.py","file_url":"https://github.com/pokaxpoka/b_pref/blob/HEAD/reward_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9d7e96fcfe3ff0f4"}},{"code_sha256_prefix":"a17d99b8eda680ff","entry":"gen_net","repo":"rll-research/bpref","repo_kind":"official","path":"reward_model.py","file_url":"https://github.com/rll-research/bpref/blob/HEAD/reward_model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a17d99b8eda680ff"}},{"code_sha256_prefix":"f707d589e5cb7e51","entry":"KCenterGreedy","repo":"rll-research/bpref","repo_kind":"official","path":"reward_model.py","file_url":"https://github.com/rll-research/bpref/blob/HEAD/reward_model.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":"f707d589e5cb7e51"}},{"code_sha256_prefix":"115ab9ed9d356045","entry":"compute_state_entropy","repo":"rll-research/bpref","repo_kind":"official","path":"agent/sac.py","file_url":"https://github.com/rll-research/bpref/blob/HEAD/agent/sac.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":"115ab9ed9d356045"}},{"code_sha256_prefix":"ad4e19d5ac571c31","entry":"linear_schedule","repo":"rll-research/bpref","repo_kind":"official","path":"train_PPO.py","file_url":"https://github.com/rll-research/bpref/blob/HEAD/train_PPO.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":"ad4e19d5ac571c31"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}