Questions tagged [actor-critic-methods]

For questions related to the family of reinforcement learning algorithms denoted by "actor-critic", where there is an actor (a policy) and a critic (a value function).

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

overcoming the original policy with offline RL

I am doing a comparison between RL and a metaheuristic algorithm. What I have found is that online RL does a good work but does not overcome the latter algorithm. In this case generating the samples ...
  • 49
0 votes
0 answers
12 views

What is the meaning about the $\alpha$ in TD3 algorithm

I am study the paper with TD3 algorithm. I am curious about the meaning of $\alpha$ while the paper prove that overestimation will be happened in a critical situation. The contents about mathematical ...
0 votes
0 answers
24 views

Why Phasic Policy Gradient (PPG) can update value function in auxiliary phase?

My questions is that how could we train the value network (separated from shared network) by using data from previous policies, which varies a lot since we collect data from different policies with ...
0 votes
0 answers
17 views

Actor-Critic Algorithm - how to design and train $V$

Background I've been watching the lecture of Standford's CS231n course, and one of the lectures (No. 14) is about RL. After talking about Q-Learning and Policy Gradients (REINFORCE algorithm), they ...
1 vote
0 answers
22 views

Linear Actor Critic for continuing task and 1 continuous action => Any comment?

I wish to implement an Actor Critic agent using linear functions for a continuing task with one continuous action. Below the resulting pseudo-code I have reached by my own (the initialization part is ...
  • 11
0 votes
0 answers
15 views

How state is combined with action in crtitic networks?

Actor-critic networks are present in deep reinforcement learning algorithms. Actor-network takes a state as input and gives action as output. Critic-network takes state and action as input and gives a ...
  • 3,251
0 votes
0 answers
8 views

Are there any general guidelines for the architecture of critic network based on actor network?

Suppose the actor-network looks like the following ...
  • 3,251
0 votes
0 answers
164 views

Tensorflow-gpu and multiprocessing

I have finished implementing an Asynchronous Advantage Actor-Critic (A3C) agent for TensorFlow (gpu). By using a single RMSprop optimizer with shared statistics. To do so, a central controller holds ...
0 votes
0 answers
23 views

As someone starting out in RL, could you help me understand the differences between actor-only, critic-only, and actor-critic methods?

I have been reading some medium articles and these three methods pop up a lot. I am wondering what the differences between these are, what are the advantages of one over the other, etc. Also from my ...
3 votes
1 answer
39 views

How do we estimate the value of a stochastic policy?

I'm learning about reinforcement learning, particularly policy gradient methods and actor-critic methods. I've noticed that many algortihms use stochastic policies during training (i.e. they select ...
1 vote
1 answer
69 views

How to implement PPO without using a Critic

I am using the standard policy gradient algorithm, REINFORCE, to solve a RL problem and was thinking about implementing Proximal Policy Optimization (PPO) to increase the sample efficiency of my ...
  • 13
1 vote
0 answers
18 views

DDPG agent with convolutional layers for feature extraction [closed]

I'm trying to come up with a definition of the critic for a DDPG agent in PyTorch using a CNN as a feature extractor. It is pretty straight forward for the actor model. However, for the critic model I ...
0 votes
1 answer
58 views

Replay buffer action range in DDPG

I have an environment where the agent action is in range [0, 1.57]. My actor network in DDPG has a tanh activation, and so the network values are in the range [-1,1]. Hence I change the scaling from [-...
0 votes
0 answers
40 views

Is there a multi-task RL algorithm that supports different action spaces for each agent?

I'm currently working on a project in which I need apply multi-task reinforcement learning. Over the same state space, each agent aims to do a separate task, but the action spaces of agents are ...
  • 1
1 vote
0 answers
108 views

Why is an action-independent baseline required to reduce variance?

I'm learning policy gradient methods. I encountered the REINFORCE algorithm with variance reduction with a baseline. I see we can use a constant or state-dependent function (e.g value function) but ...
  • 49
0 votes
1 answer
226 views

Does Value Loss in Actor Critic not decrease at all?

I am coding a problem with the Actor-Critic Method. The final loss is a summation of PolicyLoss and ValueLoss. The calculation of the PolicyLoss for each step is given at Equation Number 5 of https://...
1 vote
0 answers
86 views

How to use Actor-Critic RL with a categorical, state-dependent action space?

I have a problem where the agent is given an embedding vector to represent the state. Then it is also given a set of possible actions in the environment, let's say that the actions are each ...
  • 296
5 votes
0 answers
739 views

Why isn't a target network used for the critic in on-policy actor-critic methods?

Based on my research, I've seen so many on-policy AC approaches that utilise a critic network to estimate the value function $V$. The Bellman equation for the value function is as bellow: $$ V_\pi(s_t)...
1 vote
1 answer
157 views

How do I compute the value function when the reward is only at the end in the context of actor-critic algorithms?

Consider the actor-critic reinforcement learning setting (actor and critic parameterized by a neural network). The reward is given only at the end of the episode (or when there is a timeout there is ...
  • 131
1 vote
1 answer
104 views

Joined vs Separate optimizer for Actor-Critic

Say that I have a simple Actor-Critic architecture, (I am not familiar with Tensorflow, but) in Pytorch we need to specify the parameters when defining an optimizer (SGD, Adam, etc) and therefore we ...
  • 143
1 vote
0 answers
44 views

Setting initial values in DDPG to favor better actions

I'm working on a problem using DDPG. Is it possible to add some intelligence in the initialization phase, such that the convergence time is improved/shortened and local optima are avoided as much as ...
  • 11
1 vote
1 answer
633 views

PPO when does the update happen?

In many places, it says PPO and Actor-Critic methods in general use TD-updates, but in the loss function for PPO, the Value function loss component uses the difference between output of the value ...
  • 223
0 votes
0 answers
314 views

RLlib's Multi-agent PPO continuous actions turn into nan

After some amount of training on a custom Multi-agent sparse-reward environment using RLlib's (1.4.0) PPO network, I found that my continuous actions turn into nan (explodes?) which is probably caused ...
  • 223
2 votes
0 answers
514 views

How to interpret the training loss curves in Soft-Actor-Critic (SAC)?

I am using stable-baseline3 implementation of the Soft-Actor-Critic (SAC) algorithm. The plotted training curves look promising. However, I am not fully sure how to interpret the actor and critic ...
  • 35
0 votes
0 answers
29 views

How can I compare the results of AC1 with the results of A3C (on the CartPole environment)?

I am implementing A3C for the CartPole environment. I want to compare the results I got from A3C with the ones I got from AC1. The problem is I don't know which process to look at. If I use, let's say,...
3 votes
0 answers
199 views

How to deal with a moving target in the Lunar Lander environment with DDPG?

I have noticed that DDPG does rather well at solving environments with a static target. For example, the default of Lunar Lander, the flags do not change position. So the DDPG model learns how to get ...
1 vote
0 answers
24 views

Understanding advantage estimator in proximal policy optimization

I was reading Proximal Policy Optimization paper. It states following: The advantage estimator used is: $\hat{A}_t=-V(s_t)+r_t+\gamma r_{t+1}+...+\gamma^{T-t+1}r_{T-1}+\color{blue}{\gamma^{T-t}}V(s_T)...
  • 211
0 votes
1 answer
202 views

Can I train a DQN on the same dataset for multiple epochs?

I am trying to learn about reinforcement learning and chose the stock market to experiment with. I have minute by minute historical data on a particular stock for the past 20 years. I am using a ...
0 votes
1 answer
121 views

Relationship between Rewards and Q Value (Graph between Q(s, a) vs episodes)

I'm employing the Actor-Critic algorithm. The critic network approximates the action-value function, i.e. $Q(s, a)$, which determines how good a particular state is, when provided with an action. $Q(s,...
3 votes
0 answers
113 views

How to implement REINFORCE with eligibility traces?

The pseudocode below is taken from Barto and Sutton's "Reinforcement Learning: an introduction". It shows an actor-critic implementation with eligibility traces. My question is: if I set $\...
6 votes
1 answer
499 views

What are the advantages of RL with actor-critic methods over actor-only methods?

In general, what are the advantages of RL with actor-critic methods over actor-only (or policy-based) methods? This is not a comparison with the Q-learning series, but probably a method of learning ...
1 vote
0 answers
39 views

Why do we use big batch/epoch size in policy gradient methods (vpg specifically)?

I am re-implementing vpg and using Spinning Up as reference implementation. I noticed that the default epoch size is 4000. I also see cues in papers that big batch size is quite standard. My ...
  • 26
4 votes
1 answer
846 views

What difference does it make whether Actor and Critic share the same network or not?

I'm learning about Actor-Critic reinforcement learning algorithms. One source I encountered mentioned that Actor and Critic can either share one network (but use different output layers) or they can ...
  • 683
1 vote
1 answer
162 views

Advantage Actor Critic model implementation with Tensorflowjs

I am trying to implement an Actor Critic method that controls an RC car. For this I have implemented a simulated environment and actor critic tensorflowjs models. My intention is to train a model to ...
5 votes
1 answer
266 views

Is reinforcement learning only about determining the value function?

I started reading some reinforcement learning literature, and it seems to me that all approaches to solving reinforcement learning problems are about finding the value function (state-value function ...
  • 287
0 votes
0 answers
74 views

Variance of the Gaussian policy is not decreasing while training the agent using Soft Actor-Critic method

I've written my own version of SAC(v2) for a problem with continuous action space. While training, the losses for the value network and both q functions steadily decrease down to 0.02-0.03. The loss ...
1 vote
0 answers
84 views

How to design an observation(state) space for a simple `Rock-Paper-Scissor` game?

For weeks I've been working with this toy game of Rock-Paper-Scissor. I want to use a PPO agent learn to beat a computer ...
  • 111
0 votes
1 answer
100 views

Why would the reward of A3C with LSTM suddenly drop off after many episodes?

I am training an A3C with stacked LSTM. During initial training, my model was giving descent +ve reward. However, after many episodes, its reward just goes to zero and is continuing for a long time. ...
0 votes
1 answer
437 views

How to handle a changing in the Reinforcement Learning environment where there is increasing or decreasing in number of agents?

I'm working in A2C and I have an environment where there is increasing or decreasing in the number of agents. The action space in the environment will not change but the state will change when new ...
0 votes
0 answers
67 views

How to modify the Actor-Critic policy gradient algorithm to perform Safe exploration in Reinforcement Learning

I am trying to implement safe exploration technique in [Ref.1]. I am using Soft Actor-Critic algorithm to teach an agent to introduce a bias between 0 and 1 to a specific state of interest in my ...
0 votes
1 answer
31 views

Learning only using off-policy samples

When training policies, is there a reason we need on-policy samples? For expensive simulations, it makes sense to try and reuse samples. Say we're interested in hyperparameter tuning. Can we collect a ...
  • 101
1 vote
0 answers
49 views

When past states contain useful information, does A3C perform better than TD3, given that TD3 does not use an LSTM?

I am trying to build an AI that needs to have some information about the past states as well. Therefore, LSTMs are suitable for this. Now, I want to know that for a problem/game like Breakout, where ...
5 votes
1 answer
2k views

What is the difference between vanilla policy gradient with a baseline as value function and advantage actor-critic?

What is the difference between vanilla policy gradient (VPG) with a baseline as value function and advantage actor-critic (A2C)? By vanilla policy gradient I am specifically referring to spinning up's ...
2 votes
0 answers
59 views

What is the proof that the variance of the gradient estimate in Actor-Critic is smaller than in REINFORCE?

The intuition provided when introducing actor-critic algorithms is that the variance of its gradient estimates is smaller than in REINFORCE as, e.g., discussed here. This intuition makes sense for the ...
  • 121
1 vote
0 answers
59 views

Is this figure a correct representation of off-policy actor-critic methods?

Does this figure correctly represent the overall general idea about actor-critic methods for on-policy (left) and off-policy (right) case? I am a bit confused about the off-policy case (right figure). ...
1 vote
1 answer
140 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 ...
  • 291
1 vote
1 answer
151 views

Why is the "reward to go" replaced by Q instead of V, when transitioning from PG to actor critic methods?

While transitioning from simple policy gradient to the actor-critic algorithm, most sources begin by replacing the "reward to go" with the state-action value function (see this slide 5). I am not ...
  • 181
0 votes
1 answer
649 views

Why is my Soft Actor-Critic's policy and value function losses not converging?

I'm trying to implement a soft actor-critic algorithm for financial data (stock prices), but I have trouble with losses: no matter what combination of hyper-parameters I enter, they are not converging,...
  • 3
3 votes
1 answer
875 views

Can I apply DQN or policy gradient algorithms in the contextual bandit setting?

I have a problem which I believe can be described as a contextual bandit. More specifically, in each round, I observe a context from the environment consisting of five continuous features, and, ...
  • 165
1 vote
0 answers
138 views

Actor-Critic implementation not learning

I've implemented a vanilla actor-critic and have run into a wall. My model does not seem to be learning the optimal policy. The red graph below shows its performance in cartpole, where the algorithm ...