diff --git a/week04_[recap]_deep_learning/practice_tensorflow.ipynb b/week04_[recap]_deep_learning/practice_tensorflow.ipynb index 3d1d92bcf..b1adf8660 100644 --- a/week04_[recap]_deep_learning/practice_tensorflow.ipynb +++ b/week04_[recap]_deep_learning/practice_tensorflow.ipynb @@ -316,7 +316,7 @@ "\n", "Here's what you should see:\n", "\n", - "\n", + "\n", "\n", "Tensorboard also allows you to draw graphs (e.g. learning curves), record images & audio ~~and play flash games~~. This is useful when monitoring learning progress and catching some training issues.\n", "\n", diff --git a/week04_approx_rl/homework_lasagne.ipynb b/week04_approx_rl/homework_lasagne.ipynb index f19003152..f3334f096 100644 --- a/week04_approx_rl/homework_lasagne.ipynb +++ b/week04_approx_rl/homework_lasagne.ipynb @@ -206,7 +206,7 @@ "# Building a DQN (2 pts)\n", "Here we define a simple agent that maps game images into Qvalues using simple convolutional neural network.\n", "\n", - "![scheme](https://s18.postimg.org/gbmsq6gmx/dqn_scheme.png)" + "![scheme](https://s18.postimg.cc/gbmsq6gmx/dqn_scheme.png)" ] }, { diff --git a/week08_pomdp/practice_tensorflow.ipynb b/week08_pomdp/practice_tensorflow.ipynb index 47e547849..d7e9a6839 100644 --- a/week08_pomdp/practice_tensorflow.ipynb +++ b/week08_pomdp/practice_tensorflow.ipynb @@ -466,7 +466,7 @@ "### Training on parallel games\n", "\n", "We introduce a class called EnvPool - it's a tool that handles multiple environments for you. Here's how it works:\n", - "![img](https://s7.postimg.org/4y36s2b2z/env_pool.png)" + "![img](https://s7.postimg.cc/4y36s2b2z/env_pool.png)" ] }, { diff --git a/week09_policy_II/seminar_TRPO_pytorch.ipynb b/week09_policy_II/seminar_TRPO_pytorch.ipynb index 413d3a9f1..d97e74301 100644 --- a/week09_policy_II/seminar_TRPO_pytorch.ipynb +++ b/week09_policy_II/seminar_TRPO_pytorch.ipynb @@ -731,7 +731,7 @@ "\n", "In this section, you're invited to implement a better rollout strategy called _vine_.\n", "\n", - "![img](https://s17.postimg.org/i90chxgvj/vine.png)\n", + "![img](https://s17.postimg.cc/i90chxgvj/vine.png)\n", "\n", "In most gym environments, you can actually backtrack by using states. You can find a wrapper that saves/loads states in [the mcts seminar](https://github.com/yandexdataschool/Practical_RL/blob/master/week10_planning/seminar_MCTS.ipynb).\n", "\n", diff --git a/week09_policy_II/seminar_TRPO_tensorflow.ipynb b/week09_policy_II/seminar_TRPO_tensorflow.ipynb index b10aacf16..1084b55ad 100644 --- a/week09_policy_II/seminar_TRPO_tensorflow.ipynb +++ b/week09_policy_II/seminar_TRPO_tensorflow.ipynb @@ -670,7 +670,7 @@ "\n", "In this section, you're invited to implement a better rollout strategy called _vine_.\n", "\n", - "![img](https://s17.postimg.org/i90chxgvj/vine.png)\n", + "![img](https://s17.postimg.cc/i90chxgvj/vine.png)\n", "\n", "In most gym environments, you can actually backtrack by using states. You can find a wrapper that saves/loads states in [the mcts seminar](https://github.com/yandexdataschool/Practical_RL/blob/master/week10_planning/seminar_MCTS.ipynb).\n", "\n", diff --git a/week09_policy_II/seminar_TRPO_theano.ipynb b/week09_policy_II/seminar_TRPO_theano.ipynb index 1abb44cc1..d8e03a73f 100644 --- a/week09_policy_II/seminar_TRPO_theano.ipynb +++ b/week09_policy_II/seminar_TRPO_theano.ipynb @@ -674,7 +674,7 @@ "\n", "In this section, you're invited to implement a better rollout strategy called _vine_.\n", "\n", - "![img](https://s17.postimg.org/i90chxgvj/vine.png)\n", + "![img](https://s17.postimg.cc/i90chxgvj/vine.png)\n", "\n", "In most gym environments, you can actually backtrack by using states. You can find a wrapper that saves/loads states in [the mcts seminar](https://github.com/yandexdataschool/Practical_RL/blob/master/week10_planning/seminar_MCTS.ipynb).\n", "\n",