From f3683afb86a2d364f69fb31b58151016aa562d00 Mon Sep 17 00:00:00 2001 From: Dominik Roth Date: Tue, 22 Aug 2023 00:00:24 +0200 Subject: [PATCH] More PCA related fixes --- sbBrix/common/policies.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sbBrix/common/policies.py b/sbBrix/common/policies.py index ce6a18a..8d717cc 100644 --- a/sbBrix/common/policies.py +++ b/sbBrix/common/policies.py @@ -677,7 +677,7 @@ class ActorCriticPolicy(BasePolicy): elif isinstance(self.action_dist, StateDependentNoiseDistribution): return self.action_dist.proba_distribution(mean_actions, self.log_std, latent_pi) elif isinstance(self.action_dist, PCA_Distribution): - return self.action_dist.proba_distribution(mean_actions, self.log_std) + return self.action_dist.proba_distribution(mean_actions, th.ones_like(mean_actions) * self.log_std.exp()) else: raise ValueError("Invalid action distribution")