Questions tagged [ddpg]

For questions related to the reinforcement learning algorithm called Deep Deterministic Policy Gradient (DDPG).

Filter by
Sorted by
Tagged with
0
votes
0answers
37 views

Does Multi-Agent Deep Deterministic Policy Gradient also work with discrete action spaces?

I would like to ask if Multi-Agent Deep Deterministic Policy Gradient (MADDPG) works fine with discrete action space. DDPG works only with continuous action space, but I have read that MADDPG can also ...
0
votes
0answers
19 views

DDPG with Hindsight Experience Replay not converging properly

I am trying to train kuka arm (KukaGymEnv) on DDPG augmented with Hindsight Experience Replay (HER). The hyperparameters are as given : Actor and Critic are simple neural networks with two hidden ...
4
votes
1answer
94 views

How does the Ornstein-Uhlenbeck process work, and how it is used in DDPG?

In section 3 of the paper Continuous control with deep reinforcement learning, the authors write As detailed in the supplementary materials we used an Ornstein-Uhlenbeck process (Uhlenbeck & ...
1
vote
1answer
43 views

What do the state features of KukaGymEnv represent?

I trying to use ddpg augmented with Hindsight Experience Replay (HER) on pybullet's KukaGymEnv. To formulate the feature vector for the goal state, I need to know what do the features of the state of ...
1
vote
0answers
28 views

Using DDPG for control in multi-dimensional continuous action space?

I am relatively new to reinforcement learning, and I am trying to implement a reinforcement learning algorithm that can do continuous control in a custom environment. The state of the environment is ...
1
vote
1answer
63 views

DDPG doesn't converge for MountainCarContinuous-v0 gym environment

I am trying to implement Deep Deterministic policy gradient algorithm by referring to the paper Continuous Control using Deep Reinforcement Learning on the MountainCarContinuous-v0 gym environment. I ...
0
votes
0answers
18 views

Why is actor's loss the mean of the predicted Q values and not an error in calculating Q values, in the DDPG algorithm?

I am trying to implement the DDPG algorithm. Why is the actor's loss calculated as the negative mean of the model's predicted Q values in the states we are in? Shouldn't it be like the difference of ...
0
votes
0answers
18 views

Which is the best RL algo for continuous states but discrete action spaces problem

I am trying to train an AI with an environment where the states are continuous but the actions are discrete, that means I can not apply DDPG or TD3. Can someone please help to let know what should be ...
2
votes
0answers
144 views

Why is DDPG not learning and it does not converge?

I have used a different setting, but DDPG is not learning and it does not converge. I have used these codes 1,2, and 3 and I used different optimizers, activation functions, and learning rate but ...
1
vote
1answer
57 views

Why is the policy loss the mean of $-Q(s, \mu(s))$ in the DDPG algorithm?

I am trying to implement the DDPG algorithm based on this paper. The part that confuses me is the actor network's update. I don't understand why the policy loss is simply the mean of $-Q(s, \mu(s))$, ...
1
vote
1answer
38 views

Are there examples of agents that use a more modest number of parameters on Pendulum (or similar environments)?

I'm looking at some baseline implementations of RL agents on the Pendulum environment. My guess was to use a relatively small neural net (~100 parameters). I'm comparing my solution with some ...
2
votes
1answer
72 views

Understand the DDPG algorithm in Keras

I'm trying to understand the DDPG algorithm using Keras I found the site and started analyzing the code, I can't understand 2 things. The algorithm used to write the code presented on the page In the ...
0
votes
1answer
46 views

What reinforcement learning algorithm should I use in continuous states?

I want to use reinforcement learning in an environment I made. The exact environment doesn't really matter, but it comes down to this: The amount of different states in the environment is infinite e.g....
0
votes
0answers
45 views

Why is my DDPG agent (implemented in TensorFlow) not learning?

I am trying to implement a Reinforcement Learning algorithm called DDPG in TensorFlow 2.x on a custom gym environment. I am new to TF. So, I started with the DDPG TF 1.x implementation from pemami4911....
0
votes
0answers
30 views

2 out of 7 Observations Defined in MATLAB DDPG Reinforcement Learning Environment. Are the rest given random values?

After reading up one Deep Deterministic Policy Gradient, I found this example on MATLAB: https://www.mathworks.com/help/reinforcement-learning/ug/train-agent-to-control-flying-robot.html#...
0
votes
1answer
43 views

Is there a good website where I can learn about Deep Deterministic Policy Gradient?

Is there a good website where I can learn about Deep Deterministic Policy Gradient?
0
votes
1answer
50 views

In Deep Deterministic Policy Gradient, are all weights of the policy network updated with the same or different value?

I'm trying to understand the DDPG algorithm shown at this page. I don't know what should the result of the gradient at step 14 be. Is it a scalar that I have to use to update all the weights (so all ...
0
votes
0answers
38 views

Using deep deterministic policy gradient in OpenAI Gym to solve problems with continuous actions

I am trying to do the following: Install the OpenAI baseline algorithms from the following GitHub repository: github.com/openai/baselines by following the instructions in the readme file. Train an ...
2
votes
1answer
119 views

What made your DDPG implementation on your environment work?

I am working on scheduling problem that has inherent randomness. The dimensions of action and state spaces are 1 and 5 respectively. I am using DDPG, but it seems extremely unstable, and so far it ...
1
vote
0answers
41 views

Benchmarking SAC on Pybullet

So far I have seen TD3 and DDPG benchmarks on Pybullet environments, but I am looking for SAC benchmarks on Pybullet too, anyone can help?
1
vote
0answers
60 views

A question about the Wolpertinger algorithm (Deep RL in Large Discrete Action Spaces paper)

I am trying to reproduce the recommender task experiment from this paper. The paper suggests to embed discrete actions into continuous action space and then to use the proposed Wolpertinger agent. ...
1
vote
0answers
37 views

How can DDPG handle the discrete action space?

I am wondering how can DDPG or DPG handle the discrete action space. There are some papers saying that use Gumbel softmax with DDPG can make the discrete action problem be solved. However, will the ...
1
vote
0answers
25 views

What if the rewards induced by an environment are related to the policy too?

Assume we have a policy $\pi_{\theta}$ in a classic reinforcement learning setting, and a reward function $R^{\pi}(s,a)$ that changes as long as $\pi$ changes i.e. not only is it predefined by the ...
2
votes
2answers
124 views

Why is DDPG an off-policy RL algorithm?

In DDPG, if there are no $\epsilon$-greedy and no action noise, is DDPG an on-policy algorithm?
3
votes
1answer
69 views

Appropriate algorithm for RL problem with sparse rewards, continuous actions and significant stochasticity

I'm working on a RL problem with the following properties: The rewards are extremely sparse i.e. all rewards are 0 except the terminal non-zero reward. Ideally I would not use any reward engineering ...
1
vote
0answers
29 views

Why does the result when restoring a saved DDPG model differ significantly from the result when saving it?

I save the trained model after a certain number of episodes with the special save() function of the DDPG class (the network is saved when the reward reaches zero), but when I restore the model again ...
6
votes
2answers
137 views

Why are reinforcement learning methods sample inefficient?

Reinforcement learning methods are considered to be extremely sample inefficient. For example, in a recent DeepMind paper by Hessel et al., they showed that in order to reach human-level performance ...
1
vote
2answers
72 views

Continuous control with DDPG: How to eliminate steady state error?

Currently I'm working on a continuous control problem using DDPG as my RL algorithm. All in all, things are working out quite well, but the algorithm does not show any tendencies to eliminate the ...
2
votes
1answer
61 views

How can I implement the reward function for an 8-DOF robot arm with TRPO?

I need to get an 8-DOF (degrees of freedom) robot arm to move a specified point. I need to implement the TRPO RL code using OpenAI gym. I already have the gazebo environment. But I am unsure of how to ...
2
votes
0answers
48 views

How does adding noise to the action in DDPG help in learning?

I can't understand how playing with the action generated by the actor network in DDPG by adding the noise term helps in exploration.
3
votes
1answer
95 views

How to avoid rapid actuator movements in favor of smooth movements in a continuous space and action space problem?

I'm working on a continuous state / continuous action controller. It shall control a certain roll angle of an aircraft by issuing the correct aileron commands (in $[-1, 1]$). To this end, I use a ...
3
votes
1answer
70 views

Purpose of using actor-critic algorithms under deterministic MDP dynamics?

One of the main disadvantages of the MC Policy Gradient algorithm (REINFORCE) as described say here is the fact that it has high variance (returns, which we sample, will significantly vary from ...
2
votes
0answers
26 views

How to learn using DDPG in python solely using a timeseries datasets

I have a lengthy timeseries datasets which contains several variables (from sensors etc) to be classified as actions or states. Providing they are successfully done, I want to learn a control policy ...
2
votes
1answer
39 views

Why feed actions in later layer in Q network?

I read the DDPG paper, in which the authors state that the actions are fed only later to their Q network: Actions were not included until the 2nd hidden layer of Q. (Sec 7, Experiment Details) So ...
3
votes
0answers
251 views

Policy gradient methods for continuous action space

I have a problem I would like to tackle with RL but I am not sure if it is even doable. My agent has to figure out how to fill a very large vector (let's say from 600 to 4000 in the most complex ...
0
votes
1answer
158 views

Is DDPG just for deterministic environments?

I want to develop an AI for continuous space. I reached to DDPG algorithm that takes actions deterministically. If DDPG takes actions deterministically, should the environment also be deterministic? ...
3
votes
1answer
55 views

Training actor-critic algorithms in games with opponents

I am wondering how am I supposed to train a model using actor/critic algorithms in environments with opponents. I tried the followings (using A3C and DDPG): Play against random player. I had rather ...
3
votes
0answers
102 views

Should noise (such as OU) be decreased over time in actor / critic algorithms?

In most of RL algorithms I saw, there is a coefficient that reduces actions exploration over time, to help convergence. But in Actor-Critic, or other algorithms (A3C, DDPG, ...) used in continuous ...
4
votes
2answers
3k views

How large should the replay buffer be?

I'm learning DDPG algorithm by following the following link: Open AI Spinning Up document on DDPG, where it is written In order for the algorithm to have stable behavior, the replay buffer should ...
3
votes
1answer
97 views

Why Q2 is a more or less independant estimate in Twin Delayed DDPG (TD3)?

Twin Delayed Deep Deterministic (TD3) policy gradient is inspired by both double Q-learning and double DQN. In double Q-learning, I understand that Q1 and Q2 are independent because they are trained ...
1
vote
0answers
30 views

Should we multiply the target of actor by the importance sampling ratio when prioritized replay is applied to DDPG?

According to PER, we have to multiply the $Q$ error $\delta_i$ by the importance sampling ratio to correct the bias introduced by the imbalance sampling of PER, where importance sampling ratio is ...
3
votes
0answers
94 views

Can I use deterministic policy gradient methods for stochastic policy learning?

Can I treat a stochastic policy (over a finite action space of size $n$) as a deterministic policy (in the set of probability distribution in $\mathbb{R}^n$)? It seems to me that nothing is broken ...