### VC dimension of ball and ellipsoids in $\mathbb{R}^n$

Show that the VC-dimension of the set of all closed balls in $\mathbb{R}^n$ is at most $n+3$. Find the VC-dimension of the set of all ellipsoids in $\mathbb{R}^n$. Can anyone provide solutions to these questions?

### Why I got the same action when I train A2C when I increase the number of episodes?

I’m working on an actor-critic (A2C) reinforcement learning model but the problem when I trained the system for 3500 episodes, I start to get the same action for all my testing results. While if I trained the system for 200 episodes, I got different actions. The value of state is always different and around 850…

### Reinforcement learning CNN input weakness

I’m trying to train a network to navigate a 48×48 2D grid, and switch pixels from on to off or off to on. The agent receives a small reward if correct, and small punishment if incorrect pixel plotted. I thought, like the Deepmind “Playing Atari with Deep Reinforcement Learning” Paper, I could just use only…

### Reinforcement learning CNN input weakness

I’m trying to train a network to navigate a 48×48 2D grid, and switch pixels from on to off or off to on. The agent receives a small reward if correct, and small punishment if incorrect pixel plotted. I thought, like the Deepmind “Playing Atari with Deep Reinforcement Learning” Paper, I could just use only…

### Why Monte – Carlo epsilon soft approach cannot compute Q max (s,a)?

I am new to Reinforcement learning and am currently reading up on the estimation of Q pi(s,a) values using MC soft epsilon soft approach and chanced upon this algorithm. The link to the algorithm is found from this website. https://www.analyticsvidhya.com/blog/2018/11/reinforcement-learning-introduction-monte-carlo-learning-openai-gym/ def monte_carlo_e_soft(env, episodes=100, policy=None, epsilon=0.01): if not policy: policy = create_random_policy(env) # Create an empty…

### Why everyone is using CNN for image segmentation?

I’m newbie in artificial intelligence. I have started to research about how to do image segmentation and all the papers that I have found are about CNN. Most of them use the same network, U-NET, but with little variations: with more or less layers, different parameters values, etc.; but with not very different results. It…

### Why is this Deep Q Agent constantly learning just one action?

I’m trying to implement deep q learning in the openai gym “Taxi-v3” environment. But my agant only learns to do one action in every state. What am I doning wrong? Here is the code.

### What activation functions are better for what problems?

I’ve been reading on neural network architecture and all I read bout activation functions is that using a non-linear sigmoid “more accurately reflects real life” or for functions like hard limits it reflects “the brain neural networks more accurately.” For what type of problems are activation functions better for?