chore: small fixes

.gitignore

@@ -0,0 +1 @@
+.ipynb*

Untitled.ipynb

@@ -0,0 +1,81 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "02d39a02-17f2-4307-8d41-6903c289e9d2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import tensorflow as tf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "793e06aa-0230-433f-a92a-6c32846bc444",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "()\n"
+     ]
+    }
+   ],
+   "source": [
+    "a = tf.constant(1)\n",
+    "print(a.shape)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "4ea11dda-ab38-4e21-97e4-c318c0790ec7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(5,)\n"
+     ]
+    }
+   ],
+   "source": [
+    "b = tf.constant([1,2,3,4,5])\n",
+    "print(b.shape)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a3394f67-a3fc-4c26-887e-70c315703d65",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python (gym-env-py3.10)",
+   "language": "python",
+   "name": "gym-env-py3.10"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

test_gym.py

@@ -0,0 +1,10 @@
+import gymnasium as gym
+
+env = gym.make("CartPole-v1", render_mode="human")
+env.reset()
+
+for i in range(200):
+    env.step(env.action_space.sample())
+    env.render()
+
+env.close()

test_gym_2.py

@@ -0,0 +1,22 @@
+import gymnasium as gym
+
+env = gym.make("CartPole-v1", render_mode="human")
+env.reset()
+
+for i in range(100):
+    done = False
+    game_rew = 0
+
+    while not done:
+        action = env.action_space.sample()
+        obs, rew, terminated, truncated, info = env.step(action)
+        game_rew += rew
+
+        # Combine `terminated` (episode ended in a terminal state) 
+        # and `truncated` (time limit or another truncation condition)
+        done = terminated or truncated
+
+        if done:
+            print(f"Episode {i} finished, reward: {game_rew}")
+            env.reset()
+

test_gym_3.py

@@ -0,0 +1,30 @@
+import gymnasium as gym
+
+
+env = gym.make("CartPole-v1", render_mode="human")
+print(env.observation_space)
+print(env.action_space)
+print(env.action_space.sample())
+print(env.action_space.sample())
+print(env.observation_space.low)
+print(env.observation_space.high)
+
+env.reset()
+
+for i in range(100):
+    done = False
+    game_rew = 0
+
+    while not done:
+        action = env.action_space.sample()
+        obs, rew, terminated, truncated, info = env.step(action)
+        game_rew += rew
+
+        # Combine `terminated` (episode ended in a terminal state) 
+        # and `truncated` (time limit or another truncation condition)
+        done = terminated or truncated
+
+        if done:
+            print(f"Episode {i} finished, reward: {game_rew}")
+            env.reset()
+

test_tensorflow_1.py

@@ -0,0 +1,12 @@
+import tensorflow as tf
+
+# Create two constants: a and b
+a = tf.constant(4)
+b = tf.constant(3)
+
+# Perform a computation
+c = a + b
+
+# In TensorFlow 2.x, eager execution is enabled by default,
+# so you can directly inspect the result.
+print(c.numpy())  # This should print 7