diff --git a/agent/A2C_agent.py b/agent/A2C_agent.py
index 3b69cc3..424a147 100644
--- a/agent/A2C_agent.py
+++ b/agent/A2C_agent.py
@@ -30,7 +30,7 @@ class A2CAgent(BaseAgent):
         config = self.config
         rollout = []
         states = self.states
-        for i in range(config.rollout_length):
+        for _ in range(config.rollout_length):
             prob, log_prob, value = self.network.predict(config.state_normalizer(states))
             actions = [self.policy.sample(p) for p in prob.data.cpu().numpy()]
             next_states, rewards, terminals, _ = self.task.step(actions)
diff --git a/agent/NStepDQN_agent.py b/agent/NStepDQN_agent.py
index ceda108..d384174 100644
--- a/agent/NStepDQN_agent.py
+++ b/agent/NStepDQN_agent.py
@@ -34,7 +34,7 @@ class NStepDQNAgent(BaseAgent):
         config = self.config
         rollout = []
         states = self.states
-        for i in range(config.rollout_length):
+        for _ in range(config.rollout_length):
             q = self.network.predict(self.config.state_normalizer(states))
             actions = [self.policy.sample(v) for v in q.data.cpu().numpy()]
             next_states, rewards, terminals, _ = self.task.step(actions)
diff --git a/agent/PPO_agent.py b/agent/PPO_agent.py
index 70c00b1..7df4bbb 100644
--- a/agent/PPO_agent.py
+++ b/agent/PPO_agent.py
@@ -30,7 +30,7 @@ class PPOAgent(BaseAgent):
         config = self.config
         rollout = []
         states = self.states
-        for i in range(config.rollout_length):
+        for _ in range(config.rollout_length):
             actions, log_probs, _, values = self.network.predict(states)
             next_states, rewards, terminals, _ = self.task.step(actions.data.cpu().numpy())
             self.episode_rewards += rewards