Questions tagged [open-ai]

For questions related to the openAI, including the Gym toolkit.

Filter by
Sorted by
Tagged with
1
vote
0answers
13 views

How to integrate dict space of OpenAI gym into a reinforcement learning framework?

I am implementing a gym environment and I have several input arrays as my input (different sizes). The most simple method to integrate my environment into the gym is to use the dict space as my ...
2
votes
0answers
19 views
+50

How to formulate normalization/probability conditions on state-action spaces in Gym?

I intend to develop a custom environment for open-ai's gym. My goal is for an agent to learn (among additional objectives) dividing a certain quantity drawn from a continous action space (i.e. spaces....
1
vote
0answers
21 views

How to define observation and action space for an array-like input?

I am working on a problem, and I want to implement it as a reinforcement learning problem and integrate it into the OpenAI's gym. My states are in the form of lists of length $n$, where each element ...
1
vote
0answers
7 views

How can I add logic for invalid moves when using stable-baselines in OpenAI's gym?

I want to integrate my environment into the OpenAI's gym and then use the stable baselines library for training it. The learning method in the stable baseline is with one-line learning and you don't ...
1
vote
0answers
20 views

How should I avoid illegal states in OpenAI's gym?

I'm trying to make a gym environment for a simulation problem. In my gym environment, I have a set of illegal states which I don't want my agent to go into them. What is the easiest way to add such ...
1
vote
0answers
16 views

Pre-trained Models for Topic Modelling Transfer Learning (LDA)

I've been searching online - and so far, I've been unable to find any publicly-accessible pre-trained models that can be used for LDA Topic Modeling - Transfer Learning. Can anyone share any ...
0
votes
0answers
17 views

Stable baseline learn from online game

i created a custom environment for an online game. i want to know how can i train my model with stable baseline because learn function in stable baseline just take number of steps and in online game ...
1
vote
0answers
9 views

OpenAI spinning up convolutional networks with PPO

I am using pytorch version of PPO and I have image input that I need to process with convolutional neural networks, are there any examples on how to set up the network? I know that stable baselines ...
1
vote
0answers
23 views

Openai-gym define action space when an agent can take multiple sub-actions in a step

I'm attempting to design an action space in openai gym and hitting the following roadblock. I've looked at this post (Open AI enviroment with changing action-space after each step) which is closely ...
2
votes
0answers
30 views

Is a neuronal network able to optimize itself for speed?

I am experimenting with OpenAI Gym and reinforcement learning. As far as I understood, the environment is waiting for the agent to make a decision, so it's a sequential operation like this: ...
2
votes
2answers
176 views

Simulating successful trajectories in Montezuma's Revenge turns out to be unsuccessful

I have written code in OpenAI's gym to simulate a random playing in Montezuma's Revenge where the agent randomly samples actions from the action space and tries to play the game. A success for me is ...
4
votes
1answer
92 views

How powerful is OpenAI's Gym and Universe in board games area?

I'm a big fan of computer board games and would like to make Python chess/go/shogi/mancala programs. Having heard of reinforcement learning, I decided to look at OpenAI Gym. But first of all, I would ...
0
votes
1answer
29 views

Why is this deep Q agent constantly learning just one action?

I'm trying to implement deep q learning in the OpenAI's gym "Taxi-v3" environment. But my agent only learns to do one action in every state. What am I doning wrong? Here is the Github repository with ...
1
vote
1answer
85 views

Are there OpenAI Gym continuing environments (other than inverted pendulum) and baselines?

I would like to use OpenAI Gym to solve a continuing environment, that is, a problem with a single, never-ending episode (please note I don't mean a continuous environment with continuous state and ...
0
votes
0answers
20 views

Same implementation, but agent is not learning in Retro Pong Environment

I tried to implement the exact same python coding by Andrej Karpathy to train RL agent to play Pong, except that I migrated the environment from Gym to Retro. Everything is the same except the action ...
2
votes
1answer
64 views

Can OpenAI simulations be used in real world applications?

I know that classical control systems have been used to solve the problem of the inverted pendulum - inverted pendulum. But I've seen that people have also used machine learning techniques to solve ...
0
votes
1answer
53 views

Do algorithms like OpenAI's “think up strategies”?

I was discussing with a friend whether current AI does anything remotely similar to 'thinking' and he argued that AIs that play games must think up strategies. While thinking may not be precisely ...
1
vote
0answers
25 views

How am I getting same results 30 times faster than in original HER paper?

I am reproducing the results from Hindsight Experience Replay by Andrychowicz et. al. In the original paper they present the results below, where the agent is trained for 200 epochs. 200 epochs * 800 ...
2
votes
1answer
38 views

What is the difference between success rate and reward when dealing with binary and sparse rewards?

In OpenAI Gym reward is defined as: reward (float): amount of reward achieved by the previous action. The scale varies between environments, but the goal is ...
1
vote
0answers
24 views

Getting score values from openai gym rom

I am using the SpaceInvaders-ram-v0 from OpenAI gym. I want to extract the game's current score using the RAM values. How do I get it? I tried doing some research ...
0
votes
0answers
34 views

DQN unlearns certain OpenAI-Gym environments

I solved the OpenAI-Gym MountainCar-v0 environment using dqn(using low-state-dimensional input). When I used the same code for solving CartPole-v0 environment, the network got trained in the reverse ...
1
vote
1answer
19 views

Is there a train simulator with scripting interface?

Artificial Intelligence is usually teached with robotics in mind. The problem with car like robots is, that the amount of control which is needed is huge. A car has a position, a speed value, a ...
2
votes
1answer
485 views

Has anyone been able to solve OpenAI's hardcore bipedal walker with their implementation of DDPG?

As the question suggests, I'm trying to see if I can solve OpenAI's hardcore version of their gym's bipedal walker using OpenAI's DDPG algorithm. Below is a performance graph from my latest attempt, ...
2
votes
0answers
53 views

What is a high performing network architecture to use in a PPO2 MlpLnLstmPolicy RL model?

I am playing around with creating custom architectures in stable-baselines. Specifically I am training an agent using a PPO2 model. My question is, are there some rules of thumb or best practices in ...
0
votes
0answers
71 views

Understanding policy update in PPO2

I have a question regarding the functionality of the PPO2 algorithm together with the Stable Baselines implementation: From the original paper I know that the policy parameters $\theta$ are updated K-...
0
votes
1answer
418 views

OpenAI Spinning Up: Breakout-v0 example

I haven't been able to find any assistance / examples which could help me implement OpenAI's Spinning Up resource to solve Atari's Breakout-v0 game in the OpenAI gym. I simply want to know why the ...
0
votes
1answer
144 views

OpenAI Gym interface when reward calculation is delayed? (continuous control with considerable reaction time)

I'm about to create an OpenAI Gym environment for a flight simulator. I'm wondering, how to cope with the fact, that the result and reward for some action needs a considerable time to advance through ...
0
votes
1answer
348 views

Advice on creating a new environment using OpenAI Gym

I'm looking for some general advice here before I dive in. I'm interested in creating a new environment for OpenAI gym to provide some slightly more challenging continuous control problems than the ...
3
votes
0answers
22 views

Is it possible to insert a new map in the OpenAI Gym Taxi V.2?

I would like to train a neural network with the OpenAI Gym Taxi and see how it would react on a new map. Is it possible to insert a new map in the OpenAI Gym Taxi V.2?
0
votes
0answers
19 views

Can an OpenAI Gym Action be any object?

The gym core file simply defines action as in step(action) as an "object". I've searched for an Action object in the code without success. Can it be any python ...
1
vote
0answers
167 views

Difficulty in balancing Pendulum using Deep Reinforcement Learning Algorithm

I am using OpenAI Gym framework for reinforcement learning where I am trying solve classic control problem of balancing an Inverted Pendulum, which is similar to the "Pendulum-v0" with some changes in ...
0
votes
0answers
22 views

Turn a NES ROM into object/tile representation

So i have a rom of a hacked super mario game (it has 2 players: Mario and Luigi). Feeding in the raw pixel data of this results in very poor rewards. I was wondering if there was a way to transform ...
2
votes
1answer
226 views

Bachelor thesis in reinforcement learning

I've decided to make my bachelor thesis in RL. I am currently struggling in finding a proper problematic. I am interested in multi-agent RL with the dilemma between selfishness and cooperation. I ...
4
votes
0answers
63 views

How did the OpenAI 5 for Dota concatenate units?

I am no expert in the field of AI so I apologize if this is a simple/easy question. I was trying to implement a network similar to OpenAI's for another game and I noticed that I did not fully ...
1
vote
2answers
78 views

Running 2 NEAT nets on the same observations

So i have been playing around with neat-python. I made a program, applying neat, to play pinball on the Atari 2600. The code for that can be found in the file ...
0
votes
1answer
68 views

OpenAI-Gym excess of actions

I'm trying to replicate the DeepMind DQN paper, and actually I'm using the OpenAI-Gym enviroment. I'm trying to get a decent score with Space Invaders (using ...
6
votes
1answer
752 views

2 Player Games in OpenAI Retro

I have been using OpenAI Retro for awhile, and I wanted to experiment with two player games. By two player games, I mean co-op games like "Tennis-Atari2600" or even Pong, where 2 agents are present in ...
1
vote
2answers
82 views

OpenAI Gym for other platforms

Is there a way to run C64 / Nintendo Gameboy / other platforms in an OpenAI-Gym like environment? Seems it's Atari games only.
6
votes
3answers
1k views

Huge action space size in Reinforcement Learning

I am working on creating a 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 size ...
2
votes
0answers
3k views

How do I use GPT-2 to summarise text?

In section 3.6 of the OpenAI GPT-2 paper it mentions summarising text based relates to this, but the method is described in very high-level terms: To induce summarization behavior we add the text <...
2
votes
1answer
179 views

Which Openai Gym environment should I use to test a Temporal Difference RL Agent?

Up to now, I have been using (my version of) open AI's code, with the suggested CartPole. I have been using Monte Carlo methods, which, for cartpole, seemed to work fine. Trying to move to temporal ...
3
votes
2answers
588 views

Each training run for DDQN agent takes 2 days, and still ends up with -13 avg score, but OpenAi baseline DQN needs only an hour to converge to +18?

Status: For a few weeks now, I have been working on a Double DQN agent for the PongDeterministic-v4 environment, which you can find here. A single training run ...
0
votes
1answer
73 views

What does the Critic network evaluate in Actor Critic?

Following Pytorch's actor critic, I understand that the critic is a function mapping from the state space to the reward space, meaning, the critic approximates the state-value funcion. However, ...
4
votes
3answers
671 views

How to implement a Continuous Control of a quadruped robot with Deep Reinforcement Learning in Pybullet and OpenAI Gym?

Description I have designed this robot in URDF format and its environment in pybullet. Each leg has a minimum and maximum value of movement. What reinforcement algorithm will be best to create a ...
1
vote
1answer
394 views

DQN Breakout adding an extra negative reward to help training?

I'm trying to train a DQN, so I'm using OpenAI gym and Breakout (Breakout-v0). I have altered the reward supplied by the environment: If the episode is not completed fully, the agent gets a -10 ...
2
votes
2answers
137 views

3D environment for RL research in Academia

I'm doing my thesis on Reinforcement Learning. My focus on Partially Observable Environments like 3D Games. I want to choose a 3D platform for testing and doing ...
2
votes
0answers
270 views

How many episodes does it take for a vanilla one-step actor-critic agent to master the OpenAI BipedalWalker-v2 problem?

I'm trying to solve the OpenAI BipedalWalker-v2 by using a one-step actor-critic agent. I'm implementing the solution using python and tensorflow. I'm following this pseudo-code taken from the book ...
1
vote
0answers
59 views

Cameras for automatic customer service machine [closed]

For my university project, I am planning to build an automated customer service machine. One which recognizes when someone approaches the camera according to says hello, etc. Also, I am planning to ...
2
votes
1answer
70 views

Can the opponent's turn affect the reward for a DQN agent action?

I made an engine for a 2 players card game and now I am trying to make an environment similar to OpenAI Gym envs, to ease out the training. I fail to understand this thing however: If I use ...
2
votes
1answer
135 views

Should the exploration rate be reset after each trial in Q-learning?

As the title says, should I reset the exploration rate between trials? I am currently doing the Open AI pendulum task and after a number of trials my model started playing but did not take any ...