{"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/sample-efficient-reinforcement-learning","title":"Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraft","arxiv_id":"2003.06066","date":"2020-03-12","proceeding":null,"authors":["Christian Scheller","Yanick Schraner","Manfred Vogel"],"abstract":"Sample inefficiency of deep reinforcement learning methods is a major obstacle for their use in real-world applications. In this work, we show how human demonstrations can improve final performance of agents on the Minecraft minigame ObtainDiamond with only 8M frames of environment interaction. We propose a training procedure where policy networks are first trained on human data and later fine-tuned by reinforcement learning. Using a policy exploitation mechanism, experience replay and an additional loss against catastrophic forgetting, our best agent was able to achieve a mean score of 48. Our proposed solution placed 3rd in the NeurIPS MineRL Competition for Sample-Efficient Reinforcement Learning.","url_abs":"https://arxiv.org/abs/2003.06066v1","url_pdf":"https://arxiv.org/pdf/2003.06066v1.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":"sample-efficient-reinforcement-learning","repo_url":"https://github.com/kimbring2/DQFD_Minecraft","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"sample-efficient-reinforcement-learning","repo_url":"https://github.com/metataro/minerl_agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sample-efficient-reinforcement-learning","repo_url":"https://github.com/rishavb123/MineRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"minecraft","task_name":"Minecraft"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"experience-replay","method_name":"Experience Replay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.06066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06066"}},"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/rishavb123/MineRL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/metataro/minerl_agent","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kimbring2/DQFD_Minecraft","reach":{"status":"ok"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"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":"7ca4979ae9208b88","entry":"inputs_non_spatial","repo":"metataro/minerl_agent","repo_kind":"listed","path":"minerl_agent/agent/agent.py","file_url":"https://github.com/metataro/minerl_agent/blob/HEAD/minerl_agent/agent/agent.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":"7ca4979ae9208b88"}},{"code_sha256_prefix":"1414496026821703","entry":"inputs_spatial","repo":"metataro/minerl_agent","repo_kind":"listed","path":"minerl_agent/agent/agent.py","file_url":"https://github.com/metataro/minerl_agent/blob/HEAD/minerl_agent/agent/agent.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":"1414496026821703"}},{"code_sha256_prefix":"2a6d596d79b12390","entry":"is_single_machine","repo":"metataro/minerl_agent","repo_kind":"listed","path":"minerl_agent/impala/impala.py","file_url":"https://github.com/metataro/minerl_agent/blob/HEAD/minerl_agent/impala/impala.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":"2a6d596d79b12390"}},{"code_sha256_prefix":"1235fc6e0d3b69b8","entry":"process_inputs_craft","repo":"metataro/minerl_agent","repo_kind":"listed","path":"minerl_agent/agent/resnet_lstm_agent.py","file_url":"https://github.com/metataro/minerl_agent/blob/HEAD/minerl_agent/agent/resnet_lstm_agent.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":"1235fc6e0d3b69b8"}},{"code_sha256_prefix":"cd6d2752664b05c6","entry":"skip_action_repeats_accumulate_camera","repo":"metataro/minerl_agent","repo_kind":"listed","path":"minerl_agent/environment/actions.py","file_url":"https://github.com/metataro/minerl_agent/blob/HEAD/minerl_agent/environment/actions.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":"cd6d2752664b05c6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}