From 347d0d22cb8b1625ded764c698d7941084695ef7 Mon Sep 17 00:00:00 2001 From: Shangtong Zhang Date: Sun, 5 Nov 2017 18:58:14 -0700 Subject: [PATCH] Fix a bug --- async_worker/actor_critic.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/async_worker/actor_critic.py b/async_worker/actor_critic.py index 423452c..3ec71a7 100644 --- a/async_worker/actor_critic.py +++ b/async_worker/actor_critic.py @@ -55,7 +55,7 @@ class AdvantageActorCritic: if i == len(pending) - 1: delta = reward + config.discount * R - value.data else: - delta = reward + pending[i + 1][2].data - value.data + delta = reward + config.discount * pending[i + 1][2].data - value.data GAE = config.discount * config.gae_tau * GAE + delta loss += -log_prob.gather(1, Variable(torch.LongTensor([[action]]))) * Variable(GAE) loss += config.entropy_weight * torch.sum(torch.mul(prob, log_prob))