{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/sqil-imitation-learning-via-regularized","title":"SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards","arxiv_id":"1905.11108","date":"2019-05-27","proceeding":"ICLR 2020 1","authors":["Siddharth Reddy","Anca D. Dragan","Sergey Levine"],"abstract":"Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer from distribution shift: because the agent greedily imitates demonstrated actions, it can drift away from demonstrated states due to error accumulation. Recent methods based on reinforcement learning (RL), such as inverse RL and generative adversarial imitation learning (GAIL), overcome this issue by training an RL agent to match the demonstrations over a long horizon. Since the true reward function for the task is unknown, these methods learn a reward function from the demonstrations, often using complex and brittle approximation techniques that involve adversarial training. We propose a simple alternative that still uses RL, but does not require learning a reward function. The key idea is to provide the agent with an incentive to match the demonstrations over a long horizon, by encouraging it to return to demonstrated states upon encountering new, out-of-distribution states. We accomplish this by giving the agent a constant reward of r=+1 for matching the demonstrated action in a demonstrated state, and a constant reward of r=0 for all other behavior. Our method, which we call soft Q imitation learning (SQIL), can be implemented with a handful of minor modifications to any standard Q-learning or off-policy actor-critic algorithm. Theoretically, we show that SQIL can be interpreted as a regularized variant of BC that uses a sparsity prior to encourage long-horizon imitation. Empirically, we show that SQIL outperforms BC and achieves competitive results compared to GAIL, on a variety of image-based and low-dimensional tasks in Box2D, Atari, and MuJoCo.","url_abs":"https://arxiv.org/abs/1905.11108v3","url_pdf":"https://arxiv.org/pdf/1905.11108v3.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":"sqil-imitation-learning-via-regularized","repo_url":"https://github.com/Kaixhin/imitation-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sqil-imitation-learning-via-regularized","repo_url":"https://github.com/dnishio/DSAC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sqil-imitation-learning-via-regularized","repo_url":"https://github.com/edmundmills/basalt-competition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sqil-imitation-learning-via-regularized","repo_url":"https://github.com/Div99/IQ-Learn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"sqil-imitation-learning-via-regularized","repo_url":"https://github.com/opendilab/DI-engine/blob/main/ding/entry/serial_entry_sqil.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"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":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.11108","atlas_url":"https://app.syntology.ai/?focus=1905.11108","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1905.11108"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1905.11108\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1905.11108"},"call":"get_concepts_for_paper(arxiv_id=\"1905.11108\")"}],"by_repo":[{"repo":"Kaixhin/imitation-learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1606.03476","1801.01290"],"harvested_for_calls":[{"arxiv_id":"1606.03476","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1606.03476"},"call":"get_harvested_code_for_paper(arxiv_id=\"1606.03476\")"},{"arxiv_id":"1801.01290","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1801.01290"},"call":"get_harvested_code_for_paper(arxiv_id=\"1801.01290\")"}]},{"repo":"dnishio/DSAC","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"edmundmills/basalt-competition","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2106.12142"],"harvested_for_calls":[{"arxiv_id":"2106.12142","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.12142"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.12142\")"}]},{"repo":"Div99/IQ-Learn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1606.03476"],"harvested_for_calls":[{"arxiv_id":"1606.03476","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1606.03476"},"call":"get_harvested_code_for_paper(arxiv_id=\"1606.03476\")"}]},{"repo":"opendilab/DI-engine","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1707.01495","1901.02860","2106.01345","2304.12824"],"harvested_for_calls":[{"arxiv_id":"1707.01495","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.01495"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.01495\")"},{"arxiv_id":"1901.02860","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1901.02860"},"call":"get_harvested_code_for_paper(arxiv_id=\"1901.02860\")"},{"arxiv_id":"2106.01345","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.01345"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.01345\")"},{"arxiv_id":"2304.12824","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.12824"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.12824\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"cb36d2db1ffdba556c6e377cb3d4f99b511dc122b9897ac293905c63200232af","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}