From 94cbb863c806a77f2611ab687a1ea599949e2cb9 Mon Sep 17 00:00:00 2001 From: Joshua Spear Date: Wed, 17 Jul 2024 17:29:21 +0100 Subject: [PATCH] updated readme --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 59e1680..845d571 100644 --- a/README.md +++ b/README.md @@ -97,6 +97,7 @@ The different kinds of importance samples can also be visualised by querying the * Added explicit stochastic policies for d3rlpy * Introduced 'policy_func' which is any function/method which outputs type Union[TorchPolicyReturn, NumpyPolicyReturn] * Simplified and unified ISCallback in d3rlpy/api using PolicyFactory +* Added 'premade' doubly robust estimators for vanilla DR, weighted DR, per-decision DR and weighted per-decision DR #### 5.0.1 * Fixed bug where GreedyDeterministic couldn't handle multi-dimensional action spaces