benchmarks and pip package updates

benchmarks/a3c/README.md

@@ -6,11 +6,11 @@ The parameters used for Clipped PPO are the same parameters as described in the
 ### Inverted Pendulum A3C - 1/2/4/8/16 workers
 
 ```bash
-python3 coach.py -p Mujoco_A3C -lvl inverted_pendulum -n 1
-python3 coach.py -p Mujoco_A3C -lvl inverted_pendulum -n 2
-python3 coach.py -p Mujoco_A3C -lvl inverted_pendulum -n 4
-python3 coach.py -p Mujoco_A3C -lvl inverted_pendulum -n 8
-python3 coach.py -p Mujoco_A3C -lvl inverted_pendulum -n 16
+coach -p Mujoco_A3C -lvl inverted_pendulum -n 1
+coach -p Mujoco_A3C -lvl inverted_pendulum -n 2
+coach -p Mujoco_A3C -lvl inverted_pendulum -n 4
+coach -p Mujoco_A3C -lvl inverted_pendulum -n 8
+coach -p Mujoco_A3C -lvl inverted_pendulum -n 16
 ```
 
 <img src="inverted_pendulum_a3c.png" alt="Inverted Pendulum A3C" width="800"/>
@@ -19,7 +19,7 @@ python3 coach.py -p Mujoco_A3C -lvl inverted_pendulum -n 16
 ### Hopper A3C - 16 workers
 
 ```bash
-python3 coach.py -p Mujoco_A3C -lvl hopper -n 16
+coach -p Mujoco_A3C -lvl hopper -n 16
 ```
 
 <img src="hopper_a3c_16_workers.png" alt="Hopper A3C 16 workers" width="800"/>
@@ -28,7 +28,7 @@ python3 coach.py -p Mujoco_A3C -lvl hopper -n 16
 ### Walker2D A3C - 16 workers
 
 ```bash
-python3 coach.py -p Mujoco_A3C -lvl walker2d -n 16
+coach -p Mujoco_A3C -lvl walker2d -n 16
 ```
 
 <img src="walker2d_a3c_16_workers.png" alt="Walker2D A3C 16 workers" width="800"/>
@@ -37,7 +37,7 @@ python3 coach.py -p Mujoco_A3C -lvl walker2d -n 16
 ### Half Cheetah A3C - 16 workers
 
 ```bash
-python3 coach.py -p Mujoco_A3C -lvl half_cheetah -n 16
+coach -p Mujoco_A3C -lvl half_cheetah -n 16
 ```
 
 <img src="half_cheetah_a3c_16_workers.png" alt="Half Cheetah A3C 16 workers" width="800"/>
@@ -46,7 +46,7 @@ python3 coach.py -p Mujoco_A3C -lvl half_cheetah -n 16
 ### Ant A3C - 16 workers
 
 ```bash
-python3 coach.py -p Mujoco_A3C -lvl ant -n 16
+coach -p Mujoco_A3C -lvl ant -n 16
 ```
 
 <img src="ant_a3c_16_workers.png" alt="Ant A3C 16 workers" width="800"/>
@@ -56,7 +56,7 @@ python3 coach.py -p Mujoco_A3C -lvl ant -n 16
 ### Space Invaders A3C - 16 workers
 
 ```bash
-python3 coach.py -p Atari_A3C -lvl space_invaders -n 16
+coach -p Atari_A3C -lvl space_invaders -n 16
 ```
 
 <img src="space_invaders_a3c_16_workers.png" alt="Space Invaders A3C 16 workers" width="800"/>

benchmarks/bootstrapped_dqn/README.md

@@ -6,7 +6,7 @@ The parameters used for Bootstrapped DQN are the same parameters as described in
 ### Breakout Bootstrapped DQN - single worker
 
 ```bash
-python3 coach.py -p Atari_Bootstrapped_DQN -lvl breakout
+coach -p Atari_Bootstrapped_DQN -lvl breakout
 ```
 
 <img src="breakout_bootstrapped_dqn.png" alt="Breakout Bootstrapped DQN" width="800"/>
@@ -15,7 +15,7 @@ python3 coach.py -p Atari_Bootstrapped_DQN -lvl breakout
 ### Pong Bootstrapped DQN - single worker
 
 ```bash
-python3 coach.py -p Atari_Bootstrapped_DQN -lvl pong
+coach -p Atari_Bootstrapped_DQN -lvl pong
 ```
 
 <img src="pong_bootstrapped_dqn.png" alt="Pong Bootstrapped DQN" width="800"/>
@@ -24,7 +24,7 @@ python3 coach.py -p Atari_Bootstrapped_DQN -lvl pong
 ### Space Invaders Bootstrapped DQN - single worker
 
 ```bash
-python3 coach.py -p Atari_Bootstrapped_DQN -lvl space_invaders
+coach -p Atari_Bootstrapped_DQN -lvl space_invaders
 ```
 
 <img src="space_invaders_bootstrapped_dqn.png" alt="Space Invaders Bootstrapped DQN" width="800"/>

benchmarks/clipped_ppo/README.md

@@ -6,7 +6,7 @@ The parameters used for Clipped PPO are the same parameters as described in the
 ### Inverted Pendulum Clipped PPO - single worker
 
 ```bash
-python3 coach.py -p Mujoco_ClippedPPO -lvl inverted_pendulum
+coach -p Mujoco_ClippedPPO -lvl inverted_pendulum
 ```
 
 <img src="inverted_pendulum_clipped_ppo.png" alt="Inverted Pendulum Clipped PPO" width="800"/>
@@ -15,7 +15,7 @@ python3 coach.py -p Mujoco_ClippedPPO -lvl inverted_pendulum
 ### Inverted Double Pendulum Clipped PPO - single worker
 
 ```bash
-python3 coach.py -p Mujoco_ClippedPPO -lvl inverted_double_pendulum
+coach -p Mujoco_ClippedPPO -lvl inverted_double_pendulum
 ```
 
 <img src="inverted_double_pendulum_clipped_ppo.png" alt="Inverted Double Pendulum Clipped PPO" width="800"/>
@@ -24,7 +24,7 @@ python3 coach.py -p Mujoco_ClippedPPO -lvl inverted_double_pendulum
 ### Reacher Clipped PPO - single worker
 
 ```bash
-python3 coach.py -p Mujoco_ClippedPPO -lvl reacher
+coach -p Mujoco_ClippedPPO -lvl reacher
 ```
 
 <img src="reacher_clipped_ppo.png" alt="Reacher Clipped PPO" width="800"/>
@@ -33,7 +33,7 @@ python3 coach.py -p Mujoco_ClippedPPO -lvl reacher
 ### Hopper Clipped PPO - single worker
 
 ```bash
-python3 coach.py -p Mujoco_ClippedPPO -lvl hopper
+coach -p Mujoco_ClippedPPO -lvl hopper
 ```
 
 <img src="hopper_clipped_ppo.png" alt="Hopper Clipped PPO" width="800"/>
@@ -42,7 +42,7 @@ python3 coach.py -p Mujoco_ClippedPPO -lvl hopper
 ### Half Cheetah Clipped PPO - single worker
 
 ```bash
-python3 coach.py -p Mujoco_ClippedPPO -lvl half_cheetah
+coach -p Mujoco_ClippedPPO -lvl half_cheetah
 ```
 
 <img src="half_cheetah_clipped_ppo.png" alt="Half Cheetah Clipped PPO" width="800"/>
@@ -51,7 +51,7 @@ python3 coach.py -p Mujoco_ClippedPPO -lvl half_cheetah
 ### Walker 2D Clipped PPO - single worker
 
 ```bash
-python3 coach.py -p Mujoco_ClippedPPO -lvl walker2d
+coach -p Mujoco_ClippedPPO -lvl walker2d
 ```
 
 <img src="walker2d_clipped_ppo.png" alt="Walker 2D Clipped PPO" width="800"/>
@@ -60,7 +60,7 @@ python3 coach.py -p Mujoco_ClippedPPO -lvl walker2d
 ### Ant Clipped PPO - single worker
 
 ```bash
-python3 coach.py -p Mujoco_ClippedPPO -lvl ant
+coach -p Mujoco_ClippedPPO -lvl ant
 ```
 
 <img src="ant_clipped_ppo.png" alt="Ant Clipped PPO" width="800"/>
@@ -69,7 +69,7 @@ python3 coach.py -p Mujoco_ClippedPPO -lvl ant
 ### Swimmer Clipped PPO - single worker
 
 ```bash
-python3 coach.py -p Mujoco_ClippedPPO -lvl swimmer
+coach -p Mujoco_ClippedPPO -lvl swimmer
 ```
 
 <img src="swimmer_clipped_ppo.png" alt="Swimmer Clipped PPO" width="800"/>
@@ -78,7 +78,7 @@ python3 coach.py -p Mujoco_ClippedPPO -lvl swimmer
 ### Humanoid Clipped PPO - single worker
 
 ```bash
-python3 coach.py -p Mujoco_ClippedPPO -lvl humanoid
+coach -p Mujoco_ClippedPPO -lvl humanoid
 ```
 
 <img src="humanoid_clipped_ppo.png" alt="Humanoid Clipped PPO" width="800"/>

benchmarks/ddpg/README.md

@@ -6,7 +6,7 @@ The parameters used for DDPG are the same parameters as described in the [origin
 ### Inverted Pendulum DDPG - single worker
 
 ```bash
-python3 coach.py -p Mujoco_DDPG -lvl inverted_pendulum
+coach -p Mujoco_DDPG -lvl inverted_pendulum
 ```
 
 <img src="inverted_pendulum_ddpg.png" alt="Inverted Pendulum DDPG" width="800"/>
@@ -15,7 +15,7 @@ python3 coach.py -p Mujoco_DDPG -lvl inverted_pendulum
 ### Inverted Double Pendulum DDPG - single worker
 
 ```bash
-python3 coach.py -p Mujoco_DDPG -lvl inverted_double_pendulum
+coach -p Mujoco_DDPG -lvl inverted_double_pendulum
 ```
 
 <img src="inverted_double_pendulum_ddpg.png" alt="Inverted Double Pendulum DDPG" width="800"/>
@@ -24,7 +24,7 @@ python3 coach.py -p Mujoco_DDPG -lvl inverted_double_pendulum
 ### Reacher DDPG - single worker
 
 ```bash
-python3 coach.py -p Mujoco_DDPG -lvl reacher
+coach -p Mujoco_DDPG -lvl reacher
 ```
 
 <img src="reacher_ddpg.png" alt="Reacher DDPG" width="800"/>
@@ -33,7 +33,7 @@ python3 coach.py -p Mujoco_DDPG -lvl reacher
 ### Hopper DDPG - single worker
 
 ```bash
-python3 coach.py -p Mujoco_DDPG -lvl hopper
+coach -p Mujoco_DDPG -lvl hopper
 ```
 
 <img src="hopper_ddpg.png" alt="Hopper DDPG" width="800"/>
@@ -42,7 +42,7 @@ python3 coach.py -p Mujoco_DDPG -lvl hopper
 ### Half Cheetah DDPG - single worker
 
 ```bash
-python3 coach.py -p Mujoco_DDPG -lvl half_cheetah
+coach -p Mujoco_DDPG -lvl half_cheetah
 ```
 
 <img src="half_cheetah_ddpg.png" alt="Half Cheetah DDPG" width="800"/>
@@ -51,7 +51,7 @@ python3 coach.py -p Mujoco_DDPG -lvl half_cheetah
 ### Walker 2D DDPG - single worker
 
 ```bash
-python3 coach.py -p Mujoco_DDPG -lvl walker2d
+coach -p Mujoco_DDPG -lvl walker2d
 ```
 
 <img src="walker2d_ddpg.png" alt="Walker 2D DDPG" width="800"/>
@@ -60,7 +60,7 @@ python3 coach.py -p Mujoco_DDPG -lvl walker2d
 ### Ant DDPG - single worker
 
 ```bash
-python3 coach.py -p Mujoco_DDPG -lvl ant
+coach -p Mujoco_DDPG -lvl ant
 ```
 
 <img src="ant_ddpg.png" alt="Ant DDPG" width="800"/>
@@ -69,7 +69,7 @@ python3 coach.py -p Mujoco_DDPG -lvl ant
 ### Swimmer DDPG - single worker
 
 ```bash
-python3 coach.py -p Mujoco_DDPG -lvl swimmer
+coach -p Mujoco_DDPG -lvl swimmer
 ```
 
 <img src="swimmer_ddpg.png" alt="Swimmer DDPG" width="800"/>
@@ -78,7 +78,7 @@ python3 coach.py -p Mujoco_DDPG -lvl swimmer
 ### Humanoid DDPG - single worker
 
 ```bash
-python3 coach.py -p Mujoco_DDPG -lvl humanoid
+coach -p Mujoco_DDPG -lvl humanoid
 ```
 
 <img src="humanoid_ddpg.png" alt="Humanoid DDPG" width="800"/>

benchmarks/ddpg_her/README.md

@@ -6,7 +6,7 @@ The parameters used for DDPG HER are the same parameters as described in the [fo
 ### Fetch Reach DDPG HER - single worker
 
 ```bash
-python3 coach.py -p Fetch_DDPG_HER_baselines -lvl reach
+coach -p Fetch_DDPG_HER_baselines -lvl reach
 ```
 
 <img src="fetch_ddpg_her_reach_1_worker.png" alt="Fetch DDPG HER Reach 1 Worker" width="800"/>
@@ -15,7 +15,7 @@ python3 coach.py -p Fetch_DDPG_HER_baselines -lvl reach
 ### Fetch Push DDPG HER - 8 workers
 
 ```bash
-python3 coach.py -p Fetch_DDPG_HER_baselines -lvl push -n 8
+coach -p Fetch_DDPG_HER_baselines -lvl push -n 8
 ```
 
 <img src="fetch_ddpg_her_push_8_workers.png" alt="Fetch DDPG HER Push 8 Worker" width="800"/>
@@ -24,7 +24,7 @@ python3 coach.py -p Fetch_DDPG_HER_baselines -lvl push -n 8
 ### Fetch Slide DDPG HER - 8 workers
 
 ```bash
-python3 coach.py -p Fetch_DDPG_HER_baselines -lvl slide -n 8
+coach -p Fetch_DDPG_HER_baselines -lvl slide -n 8
 ```
 
 <img src="fetch_ddpg_her_slide_8_workers.png" alt="Fetch DDPG HER Slide 8 Worker" width="800"/>
@@ -33,7 +33,7 @@ python3 coach.py -p Fetch_DDPG_HER_baselines -lvl slide -n 8
 ### Fetch Pick And Place DDPG HER - 8 workers
 
 ```bash
-python3 coach.py -p Fetch_DDPG_HER -lvl pick_and_place -n 8
+coach -p Fetch_DDPG_HER -lvl pick_and_place -n 8
 ```
 
 <img src="fetch_ddpg_her_pick_and_place_8_workers.png" alt="Fetch DDPG HER Pick And Place 8 Workers" width="800"/>

benchmarks/dfp/README.md

@@ -6,7 +6,7 @@ The parameters used for DFP are the same parameters as described in the [origina
 ### Doom Basic DFP - 8 workers
 
 ```bash
-python3 coach.py -p Doom_Basic_DFP -n 8
+coach -p Doom_Basic_DFP -n 8
 ```
 
 <img src="doom_basic_dfp_8_workers.png" alt="Doom Basic DFP 8 workers" width="800"/>
@@ -15,7 +15,7 @@ python3 coach.py -p Doom_Basic_DFP -n 8
 ### Doom Health (D1: Basic) DFP - 8 workers
 
 ```bash
-python3 coach.py -p Doom_Health_DFP -n 8
+coach -p Doom_Health_DFP -n 8
 ```
 
 <img src="doom_health_dfp_8_workers.png" alt="Doom Health DFP 8 workers" width="800"/>
@@ -25,7 +25,7 @@ python3 coach.py -p Doom_Health_DFP -n 8
 ### Doom Health Supreme (D2: Navigation) DFP - 8 workers
 
 ```bash
-python3 coach.py -p Doom_Health_Supreme_DFP -n 8
+coach -p Doom_Health_Supreme_DFP -n 8
 ```
 
 <img src="doom_health_supreme_dfp_8_workers.png" alt="Doom Health Supreme DFP 8 workers" width="800"/>

benchmarks/dqn/README.md

@@ -6,7 +6,7 @@ The parameters used for DQN are the same parameters as described in the [origina
 ### Breakout DQN - single worker
 
 ```bash
-python3 coach.py -p Atari_DQN -lvl breakout
+coach -p Atari_DQN -lvl breakout
 ```
 
 <img src="breakout_dqn.png" alt="Breakout DQN" width="800"/>
@@ -14,7 +14,7 @@ python3 coach.py -p Atari_DQN -lvl breakout
 ### Pong DQN - single worker
 
 ```bash
-python3 coach.py -p Atari_DQN -lvl pong
+coach -p Atari_DQN -lvl pong
 ```
 
 <img src="pong_dqn.png" alt="Pong DQN" width="800"/>
@@ -22,7 +22,7 @@ python3 coach.py -p Atari_DQN -lvl pong
 ### Space Invaders DQN - single worker
 
 ```bash
-python3 coach.py -p Atari_DQN -lvl space_invaders
+coach -p Atari_DQN -lvl space_invaders
 ```
 
 <img src="space_invaders_dqn.png" alt="Space Invaders DQN" width="800"/>

benchmarks/dueling_ddqn/README.md

@@ -3,12 +3,33 @@
 Each experiment uses 3 seeds and is trained for 10k environment steps.
 The parameters used for Dueling DDQN are the same parameters as described in the [original paper](https://arxiv.org/abs/1706.01502).
 
+### Pong Dueling DDQN - single worker
+
+```bash
+coach -p Atari_Dueling_DDQN -lvl pong
+```
+
+<img src="pong_dueling_ddqn.png" alt="Pong Dueling DDQN" width="800"/>
+
+
 ### Breakout Dueling DDQN - single worker
 
 ```bash
-python3 coach.py -p Atari_Dueling_DDQN -lvl breakout
+coach -p Atari_Dueling_DDQN -lvl breakout
 ```
 
 <img src="breakout_dueling_ddqn.png" alt="Breakout Dueling DDQN" width="800"/>
 
 
+### Space Invaders Dueling DDQN - single worker
+
+```bash
+coach -p Atari_Dueling_DDQN -lvl space_invaders
+```
+
+<img src="space_invaders_dueling_ddqn.png" alt="Space Invaders Dueling DDQN" width="800"/>
+
+
+
+
+

benchmarks/dueling_ddqn_with_per/README.md

@@ -6,7 +6,7 @@ The parameters used for Dueling DDQN with PER are the same parameters as describ
 ### Breakout Dueling DDQN with PER - single worker
 
 ```bash
-python3 coach.py -p Atari_Dueling_DDQN_with_PER_OpenAI -lvl breakout
+coach -p Atari_Dueling_DDQN_with_PER_OpenAI -lvl breakout
 ```
 
 <img src="breakout_dueling_ddqn_with_per.png" alt="Breakout Dueling DDQN with PER" width="800"/>
@@ -15,7 +15,7 @@ python3 coach.py -p Atari_Dueling_DDQN_with_PER_OpenAI -lvl breakout
 ### Pong Dueling DDQN with PER - single worker
 
 ```bash
-python3 coach.py -p Atari_Dueling_DDQN_with_PER_OpenAI -lvl pong
+coach -p Atari_Dueling_DDQN_with_PER_OpenAI -lvl pong
 ```
 
 <img src="pong_dueling_ddqn_with_per.png" alt="Pong Dueling DDQN with PER" width="800"/>
@@ -24,7 +24,7 @@ python3 coach.py -p Atari_Dueling_DDQN_with_PER_OpenAI -lvl pong
 ### Space Invaders Dueling DDQN with PER - single worker
 
 ```bash
-python3 coach.py -p Atari_Dueling_DDQN_with_PER_OpenAI -lvl space_invaders
+coach -p Atari_Dueling_DDQN_with_PER_OpenAI -lvl space_invaders
 ```
 
 <img src="space_invaders_dueling_ddqn_with_per.png" alt="Space Invaders Dueling DDQN with PER" width="800"/>

benchmarks/qr_dqn/README.md

@@ -6,7 +6,7 @@ The parameters used for QR-DQN are the same parameters as described in the [orig
 ### Breakout QR-DQN - single worker
 
 ```bash
-python3 coach.py -p Atari_QR_DQN -lvl breakout
+coach -p Atari_QR_DQN -lvl breakout
 ```
 
 <img src="breakout_qr_dqn.png" alt="Breakout QR-DQN" width="800"/>
@@ -15,7 +15,7 @@ python3 coach.py -p Atari_QR_DQN -lvl breakout
 ### Pong QR-DQN - single worker
 
 ```bash
-python3 coach.py -p Atari_QR_DQN -lvl pong
+coach -p Atari_QR_DQN -lvl pong
 ```
 
 <img src="pong_qr_dqn.png" alt="Pong QR-DQN" width="800"/>

setup.py

@@ -50,7 +50,7 @@ with open(path.join(here, 'README.md'), encoding='utf-8') as f:
 install_requires=[
         'annoy==1.8.3', 'Pillow==4.3.0', 'matplotlib==2.0.2', 'numpy==1.14.5', 'pandas==0.22.0',
         'pygame==1.9.3', 'PyOpenGL==3.1.0', 'scipy==0.19.0', 'scikit-image==0.13.0',
-        'box2d==2.3.2', 'gym==0.10.5', 'gym[atari]==0.10.5', 'bokeh==0.13.0', 'futures==3.1.1', 'wxPython==4.0.1']
+        'box2d==2.3.2', 'gym==0.10.5', 'bokeh==0.13.0', 'futures==3.1.1', 'wxPython==4.0.1']
 
 # check if system has CUDA enabled GPU
 p = subprocess.Popen(['command -v nvidia-smi'], stdout=subprocess.PIPE, shell=True)