fixed bug where all values are infinite

torch_training/render_agent_behavior.py

@@ -96,14 +96,13 @@ action_dict = dict()
 final_action_dict = dict()
 scores_window = deque(maxlen=100)
 done_window = deque(maxlen=100)
-time_obs = deque(maxlen=2)
 scores = []
 dones_list = []
 action_prob = [0] * action_size
 agent_obs = [None] * env.get_num_agents()
 agent_next_obs = [None] * env.get_num_agents()
 agent = Agent(state_size, action_size, "FC", 0)
-with path(torch_training.Nets, "navigator_checkpoint500.pth") as file_in:
+with path(torch_training.Nets, "navigator_checkpoint1100.pth") as file_in:
     agent.qnetwork_local.load_state_dict(torch.load(file_in))
 
 record_images = False

utils/observation_utils.py

@@ -45,6 +45,8 @@ def norm_obs_clip(obs, clip_min=-1, clip_max=1, fixed_radius=0, normalize_to_ran
     min_obs = 0  # min(max_obs, min_gt(obs, 0))
     if normalize_to_range:
         min_obs = min_gt(obs, 0)
+    if min_obs > max_obs:
+        min_obs = max_obs
     if max_obs == min_obs:
         return np.clip(np.array(obs) / max_obs, clip_min, clip_max)
     norm = np.abs(max_obs - min_obs)