From 8eb82c86e3679e0e972e8e455228b29029b95989 Mon Sep 17 00:00:00 2001 From: Antonin Raffin Date: Tue, 11 Feb 2020 13:22:44 +0100 Subject: [PATCH] Save last mean reward --- torchy_baselines/common/callbacks.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/torchy_baselines/common/callbacks.py b/torchy_baselines/common/callbacks.py index 52cf0fb..8c0d108 100644 --- a/torchy_baselines/common/callbacks.py +++ b/torchy_baselines/common/callbacks.py @@ -232,6 +232,7 @@ class EvalCallback(EventCallback): self.n_eval_episodes = n_eval_episodes self.eval_freq = eval_freq self.best_mean_reward = -np.inf + self.last_mean_reward = -np.inf self.deterministic = deterministic self.render = render @@ -280,6 +281,7 @@ class EvalCallback(EventCallback): mean_reward, std_reward = np.mean(episode_rewards), np.std(episode_rewards) mean_ep_length, std_ep_length = np.mean(episode_lengths), np.std(episode_lengths) + self.last_mean_reward = mean_reward if self.verbose > 0: print(f"Eval num_timesteps={self.num_timesteps}, "