fixes DQN run_n_episodes using the wrong environment variable (#525)

* use argument variable instead of self variable

* chlog

Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz>

CHANGELOG.md

@@ -60,6 +60,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed the end of batch size mismatch ([#389](https://github.com/PyTorchLightning/pytorch-lightning-bolts/pull/389))
 - Fixed `batch_size` parameter for DataModules remaining ([#344](https://github.com/PyTorchLightning/pytorch-lightning-bolts/pull/344))
 - Fixed CIFAR `num_samples` ([#432](https://github.com/PyTorchLightning/pytorch-lightning-bolts/pull/432))
+- Fixed DQN `run_n_episodes` using the wrong environment variable ([#525](https://github.com/PyTorchLightning/pytorch-lightning-bolts/pull/525))
 
 ## [0.2.5] - 2020-10-12
 

pl_bolts/models/rl/dqn_model.py

@@ -171,7 +171,7 @@ def run_n_episodes(self, env, n_epsiodes: int = 1, epsilon: float = 1.0) -> List
             while not done:
                 self.agent.epsilon = epsilon
                 action = self.agent(episode_state, self.device)
-                next_state, reward, done, _ = self.env.step(action[0])
+                next_state, reward, done, _ = env.step(action[0])
                 episode_state = next_state
                 episode_reward += reward