Questions tagged [reinforcement-learning]

For questions related to reinforcement learning, i.e. a machine learning technique where we imagine an agent that interacts with an environment (composed of states) in time steps by taking actions and receiving rewards (or reinforcements), then, based on these interactions, the agent tries to find a policy (i.e. a behavioural strategy) that maximizes the cumulative reward (in the long run), so the goal of the agent is to maximize the reward.

565 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
11
votes
1answer
3k views

How to deal with a huge action space, where, at every step, there is a variable number of legal actions?

I am working on creating an RL-based AI for a certain board game. Just as a general overview of the game so that you understand what it's all about: It's a discrete turn-based game with a board of ...
6
votes
1answer
131 views

Why does a negative reward for every step really encourage the agent to reach the goal as quickly as possible?

If we shift the rewards by any constant (which is a type of reward shaping), the optimal state-action value function (and so optimal policy) does not change. The proof of this fact can be found here. ...
6
votes
0answers
147 views

Is the Bellman equation that uses sampling weighted by the Q values (instead of max) a contraction?

It is proved that the Bellman update is a contraction (1). Here is the Bellman update that is used for Q-Learning: $$Q_{t+1}(s, a) = Q_{t}(s, a) + \alpha*(r(s, a, s') + \gamma \max_{a^*} (Q_{t}(s', ...
6
votes
0answers
56 views

Normalizing Normal Distributions in Thompson Sampling for online Reinforcement Learning

In my implementation of Thompson sampling (TS) for online Reinforcement Learning, my distribution for selecting $a$ is $\mathcal{N}(Q(s, a), \frac{1}{C(s,a)+1})$ where $C(s,a)$ is the number of times $...
5
votes
1answer
2k views

How to deal with different actions for different states of the environment?

I'm new to this AI/Machine Learning and was playing around with OpenAI Gym a bit. When looking through the environments, I came across the Blackjack-v0 environment, ...
4
votes
1answer
97 views

Research into social behavior in Prisoner's Dilemma

I've been working on research into reproducing social behavior using multi-agent reinforcement learning. My focus has been on a GridWorld-style game, but I was thinking that maybe a simpler Prisoner's ...
4
votes
1answer
114 views

Multi Armed Bandits with large number of arms

I'm dealing with a (stochastic) Multi Armed Bandit (MAB) with a large number of arms. Consider a pizza machine that produces a pizza depending on an input $i$ (equivalent to an arm). The (finite) set ...
4
votes
0answers
58 views

Difficulty in agent's learning with increasing dimensions of continuous actions

I have been working on some RL project, where the policy is controlling the robot using its joint angles.Throughout the project I have noticed some phenomenon, which caught my attention. I have ...
4
votes
1answer
65 views

Can you convert a MDP problem to a Contextual Multi-Arm Bandits problem?

I'm trying to get a better understanding of Multi-Arm Bandits, Contextual Multi-Arm Bandits and Markov Decision Process. Basically, Multi-Arm Bandits is a special case of Contextual Multi-Arm Bandits ...
4
votes
0answers
64 views

Unable to train Coach for Banana-v0 Gym environment

I have just started playing with Reinforcement learning and starting from the basics I'm trying to figure out how to solve Banana Gym with coach. Essentially ...
4
votes
0answers
51 views

Ideas on a network that can translate image differences into motor commands?

I'd like to design a network that gets two images (an image under construction, and an ideal image), and has to come up with an action vector for a simple motor command which would augment the image ...
4
votes
0answers
51 views

What is the current state-of-the-art for inverse reinforcement learning on robotic control tasks?

The question is broad, since I am looking for any kind of insight into the subject. I am currently looking into the possibility for useing inverse reinforcement learning for learning robotic ...
4
votes
1answer
73 views

REINFORCE algorithm for portfolio optimization - problem while training

I'm trying to implement the Reinforce algorithm (Monte Carlo policy gradient) in order to optimize a portfolio of 94 stocks on a daily basis (I have suitable historical data to achieve this). The idea ...
4
votes
0answers
264 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 ...
4
votes
0answers
362 views

What could be causing the drastic performance drop of the DQN model on the Pong environment?

I am running a basic DQN (Deep Q-Network) on the Pong environment. Not a CNN, just a 3 layer linear neural net with ReLUs. It seems to work for the most part, but at some point, my model suffers from ...
4
votes
0answers
48 views

How define a reward function for a humanoid agent whose goal is to stand up from the ground?

I'm trying to teach a humanoid agent how to stand up after falling. The episode starts with the agent lying on the floor with its back touching the ground, and its goal is to stand up in the shortest ...
4
votes
0answers
74 views

Why is there inconsistency in the definitions of the retrace?

In Section 4.3 of paper Learning by Playing - Solving Sparse Reward Tasks from Scratch, the authors define Retrace as $$ Q^{ret}=\sum_{j=i}^\infty\left(\gamma^{j-i}\prod_{k=i}^jc_k\right)[r(s_j,a_j)+\...
4
votes
0answers
40 views

What research has been done on learning non-Markovian reward functions?

Recently, some work has been done planning and learning in Non-Markovian Decision Processes, that is, decision-making with temporally extended rewards. In these settings, a particular reward is ...
4
votes
0answers
101 views

What is a generalized MDP?

What is a generalized MDP? Here are a few sub-questions. How is it different than a "regular" MDP? How does it generalize the notion of an MDP? Why do we need a generalized MDP? Do ...
4
votes
1answer
283 views

Building AI from chess - data shape from simulation

Problem My problem is the following: Given 1000 wins, losses, and ties from a chess simulation I am using, what shape should each game be (I.e., sequence of moves leading to win/loss/tie) in order to ...
4
votes
0answers
80 views

Is there any theoretical capabilities of apply deep successor representations with A3C algorithm?

Deep Successor Representations(DSR) has given better performance in tasks like navigation when it compares to normal model-free RL tasks. Basically, DSR is a hybrid of model-free RL and Model-Based RL....
4
votes
1answer
758 views

Traveling salesman problem variant: which algorithm to choose?

I have an industrial problem which I'm trying to cast as a Traveling Salesman problem (TSP) in 3D euclidian space. There are physical limitations which implies that some subpaths may or may not be ...
3
votes
0answers
45 views

How to update the observation probabilities in a POMDP?

How can I update the observation probability for a POMDP (or HMM), in order to have a more accurate prediction model? The POMDP relies on observation probabilities that match an observation to a state....
3
votes
0answers
64 views

Policy gradient: Does it use the Markov property?

To derive the policy gradient, we start by writing the equation for the probability of a certain trajectory (e.g. see spinningup tutorial): $$ \begin{align} P_\theta(\tau) &= P_\theta(s_0, a_0, ...
3
votes
0answers
70 views

In Soft Actor Critic, why is the action sampled from current policy instead of replay buffer on value function update?

While reading the original paper of Soft Actor Critic, I came across on page number 5, under equation (5) and (6) $$ J_{V}(\psi)=\mathbb{E}_{\mathbf{s}_{t} \sim \mathcal{D}}\left[\frac{1}{2}\left(V_{\...
3
votes
1answer
46 views

What are the state-of-the-art results in OpenAI's gym environments?

What are the state-of-the-art results in OpenAI's gym environments? Is there a link to a paper/article that describes them and how these SOTA results were calculated?
3
votes
1answer
66 views

How to create a Q-Learning agent when we have a matrix as an action space?

I have a 2-dimentional matrix as an action space, the rows being a resource to be allocated, and the columns are the users that we will allocate the resources to. (I built my own RL environment) The ...
3
votes
0answers
46 views

Why is it necessary to divide the priority range according to the batch size in Prioritized Experience Replay?

According to DeepMinds's paper Prioritized Experience Replay (2016), specifically Appendix B.2.1 "Proportional prioritization" (p. 13), one should equally divide the priority range $[0, p_\...
3
votes
1answer
37 views

How to let the agent choose how to populate a state space matrix in RL (using python)

I have an agent (drone) that has to allocate subchannels for different types of User Equipment. I have represented the subchannel allocation with a 2-dimentional binary matrix, that is initialized to ...
3
votes
0answers
33 views

Why weighting by lambda that sums to 1 ensures convergence in eligibility trace?

In Sutton and Barto's Book in chapter 12, they state that if weights sum to 1, then an equation's updates have "guaranteed convergence properties". Actually why it ensures convergence? There ...
3
votes
0answers
33 views

What's an example of a simple policy but a complex value function?

Hado van Hasselt, a researcher at DeepMind, mentioned in one of his videos (from 7:20 to 8:20) on Youtube (about policy gradient methods) that there are cases when the policy is very simple compared ...
3
votes
0answers
30 views

Why is it the case that off-policy evaluation using importance sampling suffers from high variance?

The average return for trajectories, $V^{\pi_e}$(s) is often computed via the importance sampling estimate $$V^{\pi_e}(s) = \frac{1}{n}\sum_{i=1}^n\prod_{t=0}^{H}\frac{\pi_e(a_t | s_t)}{\pi_b(a_t|s_t)}...
3
votes
0answers
81 views

How to take actions at each episode and within each step of the episode in deep Q learning?

In deep Q learning, we execute the algorithm for each episode, and for each step within an episode, we take an action and record a reward. I have a situation where my action is 2-tuple $a=(a_1,a_2)$. ...
3
votes
0answers
56 views

Convergence of a delayed policy update Q-learning

I thought about an algorithm that twists the standard Q-learning slightly, but I am not sure whether convergence to the optimal Q-value could be guaranteed. The algorithm starts with an initial ...
3
votes
0answers
39 views

Does the concept of validation loss apply to training deep Q networks?

In deep learning, the concept of validation loss is to ensure that the model being trained is not currently overfitting the data. Is there a similar concept of overfitting in deep q learning? Given ...
3
votes
0answers
32 views

How do reinforcement learning and collaborative learning overlap?

How do reinforcement learning and collaborative learning overlap? What are the differences and similarities between these fields? I feel like the results I get via google do not make the distinction ...
3
votes
0answers
63 views

Can we use a Gaussian process to approximate the belief distribution at every instant in a POMDP?

Suppose $x_{t+1} \sim \mathbb{P}(\cdot | x_t, a_t)$ denotes the state transition dynamics in a reinforcement learning (RL) problem. Let $y_{t+1} = \mathbb{P}(\cdot | x_{t+1})$ denote the noisy ...
3
votes
0answers
63 views

Simplification of expected reward under the limit in continuous tasks

I was reading the average reward setting for continuous tasks from rich sutton's book (page 202, 2nd edition). There he perform a simplification over the expected reward under the limit approaching to ...
3
votes
0answers
37 views

Why do we update $W$ with $\frac{1}{\mu (A_t | S_t)}$ instead of $\frac{\pi (A_t | S_t)}{\mu (A_t | S_t)}$ in off-policy Monte Carlo control?

I had the same question when I am reading the RL textbook from Sutton Bartol as posted here. Why do we update $W$ with $\frac{1}{\mu (A_t | S_t)}$ instead of $\frac{\pi (A_t | S_t)}{\mu (A_t | S_t)}$?...
3
votes
0answers
58 views

Understanding the TensorFlow implementation of the policy gradient method

I was trying to understand the implementation of a basic policy gradient (REINFORCE) method using TensorFlow. I think I got almost everything. The only thing that still bothers me is the loss function ...
3
votes
0answers
45 views

Is Monte Carlo tree search needed in partially observable environments during gameplay?

I understand that with a fully observable environment (chess / go etc) you can run an MCTS with an optimal policy network for future planning purposes. This will allow you to pick actions for gameplay,...
3
votes
0answers
29 views

Relationship between the reward rate and the sampled reward in a Semi-Markov Decision Process

In the paper: Reinforcement learning methods for continuous-time Markov decision problems, the authors provide the following update rule for the Q-learning algorithm, when applied to Semi-Markov ...
3
votes
0answers
33 views

How does normalization of the inputs work in the context of PPO?

What does the normalization of the inputs mean in the context of PPO? At each time step of an episode, I only know the values of this time step and of the previous ones, if I take track of them. This ...
3
votes
0answers
59 views

How is the state-visitation frequency computed in “Maximum Entropy Inverse Reinforcement Learning”?

I am trying to understand the formulation of the maximum entropy Inverse RL method by Brian Ziebart. Particularly, I am stuck on how to understand the computation of state - visitation frequencies. ...
3
votes
0answers
43 views

Representation of state space, action space and reward system for Reinforcement Learning problem

I am trying to solve the problem of an agent dynamically discovering(start with no information about the environment) the environment and to explore as much of the environment as possible without ...
3
votes
0answers
76 views

What are the guidelines for defining a reward function in reinforcement learning (bandit problem)?

I'm working currently on a problem and I'm using RL (bandit problem). In my system, I have an agent that chooses an action among $k$ possible actions, and a user that decides whether the agent ...
3
votes
0answers
118 views

How to correctly implement self-play with DQN?

I have an environment where an agent faces an equal opponent, and while I've achieved OK performance implementing DQN and treating the opponent as a part of the environment, I think performance would ...
3
votes
0answers
51 views

Is this a good approach to solving Atari's “Montezuma's Revenge”?

I'm new to Reinforcement Learning. For an internship, I am currently training Atari's "Montezuma's Revenge" using a double Deep Q-Network with Hindsight Experience Replay (HER) (see also ...
3
votes
1answer
90 views

What is the purpose of argmax in the PPO algorithm?

I'm kinda new to machine learning and still not too solid on math and particularly calculus. I'm currently trying to implement PPO algorithm as described in the spiningUp website : This line is ...
3
votes
1answer
70 views

How does the optimization process in hindsight experience replay exactly work?

I was reading the following research paper Hindsight Experience Replay. This is the paper that introduces a concept called Hindsight Experience Replay (HER), which basically attempts to alleviate the ...

1
2 3 4 5
12