Codesota · Models · CQL (Conservative Q-Learning)UC Berkeley1 results · 1 benchmarks
Model card

CQL (Conservative Q-Learning).

UC Berkeleyopen-sourceConservative Q-Learning — adds a regularizer to Q-values to penalize out-of-distribution actions

Kumar et al. NeurIPS 2020. One of the most widely cited offline RL baselines.

§ 02 · Benchmarks

Every benchmark CQL (Conservative Q-Learning) has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01d4rl-halfcheetah-mediumnormalized_return44.0%#3/32026-04-20source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 05 · Related models

Other UC Berkeley models scored on Codesota.

SAC (state-based)
1 result
IQL (Implicit Q-Learning)
0 results
Octo-Base
0 results
SAC
0 results
§ 06 · Sources & freshness

Where these numbers come from.

codesota-api
1
result
0 of 1 rows marked verified.