Papers › Self-Imitation Learning via Generalized Lower Bound Q-learning

Self-Imitation Learning via Generalized Lower Bound Q-learning

12 Jun 2020NeurIPS 2020 12arXiv:2006.07442archive 2025-07-28

Yunhao Tang

Self-imitation learning motivated by lower-bound Q-learning is a novel and effective approach for off-policy learning. In this work, we propose a n-step lower bound which generalizes the original return-based lower-bound Q-learning, and introduce a new family of self-imitation learning algorithms. To provide a formal motivation for the potential performance gains provided by self-imitation learning, we show that n-step lower bound Q-learning achieves a trade-off between fixed point bias and contraction rate, drawing close connections to the popular uncorrected n-step Q-learning. We finally show that n-step lower bound Q-learning is a more robust alternative to return-based self-imitation learning and uncorrected n-step, over a wide range of continuous control benchmark tasks.

PaperPDFConference PDFCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2006.07442")

Code

Syntology Ran 16 of 20 code samples harvested from 2 repositories linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · violated contract; 3 ran · our draft was wrong; 11 ran with no contract checked.

By repository: found in paper text by Syntology: 20 samples from 2 repositories, 16 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

openai/spinningup found in paper text by SyntologyMIT report
junhyukoh/self-imitation-learning found in paper text by Syntology report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

20 samples harvested; 16 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · violated contract
3ran · our draft was wrong
11ran
4unverified

Licence: 0 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

MinSegmentTree junhyukoh/self-imitation-learning/baselines/common/self_imitation.py found in paper text by Syntology ran MIT (permissive) · ae840f19840ded1e · report
ReplayBuffer junhyukoh/self-imitation-learning/baselines/common/self_imitation.py found in paper text by Syntology ran MIT (permissive) · 92fcff634a9f6c9e · report
SegmentTree junhyukoh/self-imitation-learning/baselines/common/self_imitation.py found in paper text by Syntology ran MIT (permissive) · a8ec19e70d73f9c2 · report
SumSegmentTree junhyukoh/self-imitation-learning/baselines/common/self_imitation.py found in paper text by Syntology ran MIT (permissive) · 7d650bc8cab9fa52 · report
all_bools openai/spinningup/spinup/utils/run_utils.py found in paper text by Syntology ran MIT (permissive) · 2103e65a90ce7a04 · report
colorize openai/spinningup/spinup/utils/logx.py found in paper text by Syntology ran MIT (permissive) · 7e36f1c357c4618d · report
combined_shape openai/spinningup/spinup/algos/pytorch/ddpg/core.py found in paper text by Syntology ran · our draft was wrong MIT (permissive) · 57542f87e248db45 · report
convert_json openai/spinningup/spinup/utils/serialization_utils.py found in paper text by Syntology ran · our draft was wrong MIT (permissive) · fbc505a5dac82646 · report
count_vars openai/spinningup/spinup/algos/pytorch/ddpg/core.py found in paper text by Syntology ran MIT (permissive) · 4cca5e460067b900 · report
discount_with_dones junhyukoh/self-imitation-learning/baselines/common/self_imitation.py found in paper text by Syntology ran · violated contract fingerprinted MIT (permissive) · 874462e54e7cc379 · report
flat_concat openai/spinningup/spinup/utils/mpi_tf.py found in paper text by Syntology ran MIT (permissive) · f29202d8108bccd3 · report
get_all_datasets openai/spinningup/spinup/utils/plot.py found in paper text by Syntology ran MIT (permissive) · 62314e3b8ca6edfc · report
get_datasets openai/spinningup/spinup/utils/plot.py found in paper text by Syntology ran MIT (permissive) · e642bb98eca55069 · report
is_json_serializable openai/spinningup/spinup/utils/serialization_utils.py found in paper text by Syntology ran · violated contract MIT (permissive) · 9ca8b8e45f7fbebf · report
mlp openai/spinningup/spinup/algos/pytorch/ddpg/core.py found in paper text by Syntology ran · our draft was wrong MIT (permissive) · 7569e2a512ec417c · report
valid_str openai/spinningup/spinup/utils/run_utils.py found in paper text by Syntology ran fingerprinted MIT (permissive) · c6bdd181afa1fdf7 · report
PrioritizedReplayBuffer junhyukoh/self-imitation-learning/baselines/common/self_imitation.py found in paper text by Syntology unverified MIT (permissive) · 3d40ed2237ec8f20 · report
SelfImitation junhyukoh/self-imitation-learning/baselines/common/self_imitation.py found in paper text by Syntology unverified MIT (permissive) · 1a23890f034cf35a · report
assign_params_from_flat openai/spinningup/spinup/utils/mpi_tf.py found in paper text by Syntology unverified MIT (permissive) · 042875cf711accd0 · report
restore_tf_graph openai/spinningup/spinup/utils/logx.py found in paper text by Syntology unverified MIT (permissive) · 8a70bbd1276e274c · report

Tasks

Continuous ControlImitation LearningQ-Learningcontinuous-control

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Q-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections