diff --git a/README.md b/README.md
index 85dffa1..1b8928b 100644
--- a/README.md
+++ b/README.md
@@ -1,41 +1,26 @@
-# SAC+CPC implementaiton in PyTorch
-
-#
+# CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
 
 ## Instructions
-To train an SAC+CPC agent on the `cheetah run` task from image-based observations  run:
+To train a CURL agent on the `cartpole swingup` task from image-based observations run `bash script/run.sh` from the root of this directory. The `run.sh` file contains the following command, which you can modify to try different environments / hyperparamters.
 ```
-CUDA_VISIBLE_DEVICES=4 python train_cpc.py \
-    --dmc2gym \
-    --domain_name reacher \
-    --task_name easy \
+CUDA_VISIBLE_DEVICES=0 python train.py \
+    --domain_name cartpole \
+    --task_name swingup \
     --encoder_type pixel \
-    --decoder_type identity \
-    --action_repeat 4 --frame_stack 1 \
-    --save_tb --save_video --num_train_steps 1000000 \
-    --work_dir ./tmp/dmc/reacher_easy_cpc \
-    --agent sac_cpc \
-    --seed 2 --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 10000
-
-CUDA_VISIBLE_DEVICES=7 python train.py \
-    --domain_name walker \
-    --task_name walk --dmc2gym \
-    --encoder_type pixel \
-    --decoder_type identity \
-    --action_repeat 4 \
-    --save_tb --pre_transform_image_size 84 --image_size 84 \
-    --work_dir ./tmp/icml/vanilla_sac/ML0107walker_vanilla_sac \
-    --agent sac_ae --frame_stack 3 \
+    --action_repeat 8 \
+    --save_tb --pre_transform_image_size 100 --image_size 84 \
+    --work_dir ./tmp \
+    --agent curl_sac --frame_stack 3 \
     --seed -1 --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 10000 --batch_size 128 --num_train_steps 1000000 
 ```
-Try - reducing log std actor max from 2->1 or increase 2->3 
 
+This will store data related to the run in the specified `working_dir`. To enable model or video saving, use the `--save_model` or `--save_video` flags. For all available flags, inspect `train.py`. To visualize progress with tensorboard run:
 
-This will produce 'log' folder, where all the outputs are going to be stored including train/eval logs, tensorboard blobs, and evaluation episode videos. One can attacha tensorboard to monitor training by running:
 ```
-tensorboard --logdir log
+tensorboard --logdir log --port 6006
 ```
-and opening up tensorboad in your browser.
+
+and go to `localhost:6006` in your browser. If you're running headlessly, try port forwarding with ssh.
 
 The console output is also available in a form:
 ```
@@ -49,9 +34,9 @@ S - total number of environment steps
 D - duration in seconds to train 1 episode
 R - episode reward
 BR - average reward of sampled batch
-ALOSS - average loss of actor
-CLOSS - average loss of critic
-RLOSS - average reconstruction loss (only if is trained from pixels and decoder)
+A_LOSS - average loss of actor
+CR_LOSS - average loss of critic
+CU_LOSS - average loss of the CURL encoder
 ```
 while an evaluation entry:
 ```
diff --git a/curl_sac.py b/curl_sac.py
index 99c0f2d..aa26aee 100644
--- a/curl_sac.py
+++ b/curl_sac.py
@@ -442,7 +442,7 @@ class CurlSacAgent(object):
         self.encoder_optimizer.step()
         self.cpc_optimizer.step()
         if step % self.log_interval == 0:
-            L.log('train_cpc/cpc_loss', loss, step)
+            L.log('train_curl/curl_loss', loss, step)
 
 
     def update(self, replay_buffer, L, step):
diff --git a/logger.py b/logger.py
index 8e31fd4..e35d6a0 100644
--- a/logger.py
+++ b/logger.py
@@ -13,8 +13,8 @@ FORMAT_CONFIG = {
         'train': [
             ('episode', 'E', 'int'), ('step', 'S', 'int'),
             ('duration', 'D', 'time'), ('episode_reward', 'R', 'float'),
-            ('batch_reward', 'BR', 'float'), ('actor_loss', 'ALOSS', 'float'),
-            ('critic_loss', 'CLOSS', 'float'), ('ae_loss', 'RLOSS', 'float')
+            ('batch_reward', 'BR', 'float'), ('actor_loss', 'A_LOSS', 'float'),
+            ('critic_loss', 'CR_LOSS', 'float'), ('curl_loss', 'CU_LOSS', 'float')
         ],
         'eval': [('step', 'S', 'int'), ('episode_reward', 'ER', 'float')]
     }
diff --git a/scripts/long_experiments.sh b/scripts/long_experiments.sh
deleted file mode 100755
index e69de29..0000000
diff --git a/scripts/run.sh b/scripts/run.sh
index 90016db..d44d7d2 100755
--- a/scripts/run.sh
+++ b/scripts/run.sh
@@ -1,66 +1,9 @@
-
-# curl cheetah, crop 76 > 64, grayscale + random crop, deep stack
-# batch size = 256 instead of 128. maybe 256 makes 64x64 work. And, try using 512 with 64x64.
-# then try adam LR (smaller) - 3e-4... You can try 2e-4 and 5e-4. 
-# try using the stochastic policy for eval. (you can do later.. for now the important thing is to run ablations.)
-# try bigger frame stack, maybe 8.
-#     parser.add_argument('--critic_tau', default=0.01, type=float) # try 0.05 or 0.1
-# run 1: batch 256, first try with 84 
-# run 2: batch 512, first try with 84, then try 64, then try their encoder
-# run 3: batch 256, first try with 84 
-# run 4: batch 512, first try with 84, then try 64, then try their encoder
-# run 5: 2e-4 lr for all
-# run 6: 5e-4 for all
-# run 7: critic higher tau, 0.05
-
-# try stochastic critic eval
-CUDA_VISIBLE_DEVICES=1 python train_cpc.py \
-    --domain_name cheetah \
-    --task_name run --dmc2gym \
+CUDA_VISIBLE_DEVICES=5 python train.py \
+    --domain_name cartpole \
+    --task_name swingup \
     --encoder_type pixel \
-    --decoder_type identity \
-    --action_repeat 4 --batch_size 256 \
-    --save_tb --work_dir ./tmp/icml/feb2cheetah/curl_cheetah_b256_84 \
-    --agent sac_cpc --frame_stack 3 --pre_transform_image_size 100 --image_size 84 \
-    --seed 23 --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 10000 --batch_size 128 --num_train_steps 3000000 &
-
-CUDA_VISIBLE_DEVICES=2 python train_cpc.py \
-    --domain_name cheetah \
-    --task_name run --dmc2gym \
-    --encoder_type pixel \
-    --decoder_type identity \
-    --action_repeat 4 \
-    --save_tb --work_dir ./tmp/icml/feb2cheetah/curl_cheetah_b512_84 \
-    --agent sac_cpc --frame_stack 3 --pre_transform_image_size 100 --image_size 84 \
-    --seed 23 --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 20000 --batch_size 512 --num_train_steps 3000000 & 
-
-CUDA_VISIBLE_DEVICES=3 python train.py \
-    --domain_name cheetah \
-    --task_name run --dmc2gym \
-    --encoder_type pixel \
-    --decoder_type identity \
-    --action_repeat 4 --batch_size 256 \
-    --save_tb --work_dir ./tmp/icml/feb2cheetah/rad_cheetah_b256_84 \
-    --agent sac_ae --frame_stack 3 --pre_transform_image_size 100 --image_size 84 \
-    --seed 23 --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 20000 --batch_size 128 --num_train_steps 3000000 & 
-
-CUDA_VISIBLE_DEVICES=4 python train.py \
-    --domain_name cheetah \
-    --task_name run --dmc2gym \
-    --encoder_type pixel \
-    --decoder_type identity \
-    --action_repeat 4 \
-    --save_tb --work_dir ./tmp/icml/feb2cheetah/rad_cheetah_b512_84 \
-    --agent sac_ae --frame_stack 3 --pre_transform_image_size 100 --image_size 84 \
-    --seed 23 --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 20000 --batch_size 512 --num_train_steps 3000000 & 
-
-CUDA_VISIBLE_DEVICES=7 python train_cpc.py \
-    --domain_name cheetah \
-    --task_name run --dmc2gym \
-    --encoder_type pixel \
-    --decoder_type identity \
-    --action_repeat 4 \
-    --save_tb --work_dir ./tmp/icml/feb2cheetah/curl_cheetah_b256_84_lr3e4 \
-    --agent sac_cpc --frame_stack 3 --pre_transform_image_size 100 --image_size 84 \
-    --seed 23 --encoder_lr 3e-4 --critic_lr 3e-4 --actor_lr 3e-4 \
-    --eval_freq 20000 --batch_size 256 --num_train_steps 3000000 
\ No newline at end of file
+    --action_repeat 8 \
+    --save_tb --pre_transform_image_size 100 --image_size 84 \
+    --work_dir ./tmp/cartpole \
+    --agent curl_sac --frame_stack 3 \
+    --seed -1 --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 10000 --batch_size 128 --num_train_steps 1000000 
\ No newline at end of file
diff --git a/scripts/short_experiments.sh b/scripts/short_experiments.sh
deleted file mode 100755
index e69de29..0000000