user avatar
user avatar
user avatar
jgauth
  • Member for 2 years, 1 month
  • Last seen more than 1 year ago
5 votes
1 answer
392 views

How does being on-policy prevent us from using the replay buffer with the policy gradients?

4 votes
1 answer
302 views

What is the advantage of using more than one environment with the advantage actor-critic?

2 votes
1 answer
500 views

Why do we calculate the mean squared error loss to improve the value approximation in Advantage Actor-Critic Algorithm?

2 votes
1 answer
274 views

What are the most common deep reinforcement learning algorithms and models apart from DQN?

2 votes
2 answers
195 views

Advantage computed the wrong way?

2 votes
1 answer
811 views

Why isn't my implementation of A2C for the the atari pong game converging?

1 vote
0 answers
56 views

Using a model-based method to build an accurate day trading environment model

1 vote
1 answer
208 views

Why are the rewards of my RL agent for the Atari Breakout game decreasing after a certain number of episodes?

1 vote
0 answers
217 views

Replace epsilon greedy action selection and the standard DQN by an Independent Gaussian Noise Network Model

1 vote
1 answer
68 views

Is there a good and easy paper to code policy gradient algorithms (REINFORCE) from scratch?

1 vote
1 answer
152 views

What does the notation $\partial \theta_{\pi}$ mean in this actor-critic update rule?

1 vote
0 answers
51 views

Subtracting the entropy from our policy gradient will prevent our agent from being stuck in the local minimum?

1 vote
1 answer
154 views

Once the environments are vectorized, how do I have to gather immediate experiences for the agent?

1 vote
0 answers
59 views

Atari Breakout Infrastructure

1 vote
0 answers
169 views

Why isn't my DQN agent improving when trained on Atari Breakout?