diff --git a/docs/CFU_Installation_Steps.md b/docs/CFU_Installation_Steps.md
deleted file mode 100644
index 8c9907f7..00000000
--- a/docs/CFU_Installation_Steps.md
+++ /dev/null
@@ -1,23 +0,0 @@
-# Arch gym - CFU Playground installation
-
-An installation script has been provided to install all dependencies in one go. It's recommended to run this as the superuser, as it asks for your password during execution:
-
-For e.g. use ```sudo bash ./install_sim.sh cfu```, if you want to use bash. You can also set the current terminal to superuser using ```sudo su```, and then run the script normally as ```./install_sim cfu```
-
-If you want to manually install cfu, follow these steps:
-- In the oss-arch-gym directory, run 
-```sh
-git submodule update --init sims/CFU-Playground/CFU-Playground
-```
-
-- Move into the CFU Playrgoud directory:
-```sh 
-cd sims/CFU-Playground/CFU-Playground
-```
-- Run the following from this location:
-```sh
-./scripts/setup
-./scripts/setup_vexriscv_build.sh
-make install-sf
-```
-Now you should be able to use the CFU-env gym environment.
\ No newline at end of file
diff --git a/docs/Vizier_installation.md b/docs/Vizier_installation.md
deleted file mode 100644
index d214975e..00000000
--- a/docs/Vizier_installation.md
+++ /dev/null
@@ -1,10 +0,0 @@
-# Arch gym - Vizier installation guide
-
-An installation script has been provided to install vizier and its dependencies easily. To properly install vizier into arch-gym, ensure that you have installed the arch-gym conda environment.
-
-Open a shell in the oss-arch-gym directory, and run the following commands:
-
-- ```conda activate arch-gym```
-- ```./install_sim.sh viz```
-
-This will install vizier and its dependencies into the arch-gym environment.
\ No newline at end of file
diff --git a/sims/CFU-Playground/train_randomwalker.py b/sims/CFU-Playground/train_randomwalker.py
deleted file mode 100644
index 3faa54c5..00000000
--- a/sims/CFU-Playground/train_randomwalker.py
+++ /dev/null
@@ -1,69 +0,0 @@
-from absl import flags, app
-import os
-import envlogger
-from envlogger.testing import catch_env   
-import sys
-
-sys.path.append('../../arch_gym/envs')
-import CFUPlayground_wrapper
-
-flags.DEFINE_string('workload', 'micro_speech', 'workload the processor is being optimized for')
-flags.DEFINE_integer('num_steps', 1, 'Number of training steps.')
-flags.DEFINE_bool('use_envlogger', True, 'Use envlogger to log the data.') 
-flags.DEFINE_string('traject_dir', 'random_walker_trajectories', 'Directory to save the dataset.')
-flags.DEFINE_string('summary_dir', ".", 'Directory to save the dataset.')
-flags.DEFINE_string('reward_formulation', 'both', 'The kind of reward we are optimizing for')
-
-FLAGS = flags.FLAGS
-
-envdm = catch_env.Catch()
-
-
-def wrap_in_envlogger(env,envlogger_dir):
-   metadata = {
-      'agent_type' : 'RandomWalker',
-      'num_steps': FLAGS.num_steps,
-      'env_type': type(env).__name__,
-   }  
-   if FLAGS.use_envlogger:
-      env = envlogger.EnvLogger(env, data_directory=envlogger_dir, max_episodes_per_file=1000, metadata=metadata)
-      return env
-   else:
-      return env
-
-def main(_):
-   env = CFUPlayground_wrapper.make_cfuplaygroundEnv(target_vals = [1000, 1000],rl_form='random_walker', reward_type = FLAGS.reward_formulation, max_steps = FLAGS.num_steps, workload = FLAGS.workload)
-   # experiment name 
-   exp_name =  FLAGS.workload + "_num_steps_" + str(FLAGS.num_steps) + "_reward_type+" + FLAGS.reward_formulation
-   # append logs to base path
-   log_path = os.path.join(FLAGS.summary_dir, 'random_walker_logs', FLAGS.reward_formulation, exp_name)
-    # get the current working directory and append the exp name
-   traject_dir = os.path.join(FLAGS.summary_dir, FLAGS.traject_dir, FLAGS.reward_formulation, exp_name)
-    # check if log_path exists else create it
-   if not os.path.exists(log_path):
-        os.makedirs(log_path)
-   if FLAGS.use_envlogger:
-        if not os.path.exists(traject_dir):
-            os.makedirs(traject_dir)
-   env = wrap_in_envlogger(env, traject_dir)
-   env.reset()
-
-   for step in range(FLAGS.num_steps):
-      print("________________________________________________________\n",
-             "________________________________________________________\n",
-             "________________________________________________________\n",
-             "________________________________________________________\n")
-      print("ITERATION NUMBER: ",step+1," OUT OF: ",FLAGS.num_steps)
-      print("________________________________________________________\n",
-             "________________________________________________________\n",
-             "________________________________________________________\n",
-             "________________________________________________________\n")
-      # generate random actions
-      action = env.action_space.sample()
-
-      obs, reward, done, info = env.step(action)
-
-   env.close()
-      
-if __name__ == '__main__':
-   app.run(main)