Playing Atari with Deep Reinforcement Learning · HackerPapers discussions

Playing Atari with Deep Reinforcement Learning — mentioned by gary_0

Sun, 21 Jan 2024 01:01:07 GMT

The rules of Go are not exactly "programmed in" to AlphaGo; they are only provided so the model knows what the valid moves and win conditions are as it self-trains. The latest versions of the model can be quickly adapted to play other games[0] and MuZero can "master games without knowing their rules"[1]. Also, some of DeepMind's earliest work was a deep reinforcement learning model that could play seven different Atari games with no adjustments needed to switch games[2]. [0] https://en.wikipedia.org/wiki/AlphaGo_Zero [1] https://en.wikipedia.org/wiki/MuZero [2] https://arxiv.org/abs/1312.5602

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by phonebucket

Tue, 24 Jan 2023 15:29:18 GMT

A lot depends on what you're interested in. Some papers that are runnable on a laptop CPU (so long as you stick to small image sizes/tasks): 1) Generative Adversarial Networks (https://arxiv.org/abs/1406.2661). Good practice to have a custom training loops, different optimisers and networks etc. 2) Neural Style Transfer (https://arxiv.org/abs/1508.06576). Nice to be able to manipulate pretrained networks and intercept intermediate layers. 3) Deep Image Prior (https://arxiv.org/abs/1711.10925). Nice low-data exercise in building out an autoencoder. 4) Physics Informed Neural Networks…

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — HN submission

Mon, 29 Jul 2019 18:17:41 GMT

Playing Atari with Deep Reinforcement Learning (2013)

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by ap46

Tue, 11 Apr 2017 02:11:18 GMT

PLAGIARISM Third paragraph of Intro in original DeepMind paper https://arxiv.org/pdf/1312.5602.pdf & Second paragraph of Intro(5th line) of this project. http://nihit.github.io/resources/spaceinvaders.pdf They didn't even bother to do something original except for using the RAM state instead of pixel values like the original paper. It's something that's easily doable with the openAI gym. This seems like a course project at stanford.

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by komaromy

Tue, 03 Jan 2017 04:48:57 GMT

Looks really cool. I recently hit a roadblock when trying to implement the original DeepMind Atari algorithm [0] with TensorFlow. They don't mention this in the paper, but the network wasn't trained to convergence at each training step (maybe this would be obvious to people more well-versed in deep learning, but it wasn't to me coming from a classical RL background). As it turns out, TensorFlow's optimizers don't have a way to manually terminate training before convergence. That meant I was getting through several orders of magnitude fewer training steps than the DeepMind team did, even when…

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by visarga

Fri, 19 Aug 2016 10:15:01 GMT

> once we have a comprehensive AI program that can play many kinds of games Before AlphaGo, DeepMind released a reinforcement learning algorithm that could play many Atari games just from the raw pixels on the screen, in many games surpassing humans. The same algorithm. https://arxiv.org/pdf/1312.5602.pdf Reinforcement learning is a general framework for learning behavior from acting in an environment with the purpose to maximize a reward. It can be used, and was used, in multiple domains. AlphaGo used RL as well. Saying that AlphaGo is limited because it only knows to play one game, is like…

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by ktta

Mon, 20 Jun 2016 18:07:03 GMT

I find it really interesting that Goal 4 is a game playing agent. Deepmind has been focussing on this since the beginning[0] and actually has great progress as far as Atari games go[1]. And DeepMind is able to use a single agent rather than a different specific one for each game. I wonder if OpenAI wants to go in a different direction although RL has considerable success. Whereas the other goals definitely need a lot of work before they are "real-world" functional, especially Goal 3. But of course that depends on their definition of 'useful'. [0]:https://www.youtube.com/watch?v=rbsqaJwpu6A…

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by jkldotio

Tue, 10 May 2016 10:13:37 GMT

The examples where this happens have always seemed fairly weak to me. How many of the grave errors, not just where it's the wrong type of animal or container but actually thinking it's radically different, survive an application of Gaussian blur? Furthermore self-driving cars are a combination of signals; you are going to need to simultaneously fool both LIDAR and cameras. On top of that you are going need to fool them over multiple frames, while the sensors get a different angle on the subject as the car moves. For example in the first Deep Q-learning paper, "Playing Atari with Deep…

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by daveguy

Mon, 21 Mar 2016 12:19:19 GMT

Raw pixels. And the score. The score was separate, or rather a signal representing increased score. Relevant quote from the paper: "The emulator’s internal state is not observed by the agent; instead it observes an image xt ∈ Rd from the emulator, which is a vector of raw pixel values representing the current screen. In addition it receives a reward rt representing the change in game score." The paper: http://arxiv.org/abs/1312.5602

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by sharemywin

Thu, 26 Feb 2015 03:07:00 GMT

PDF: http://arxiv.org/pdf/1312.5602v1.pdf

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by nl

Wed, 25 Feb 2015 21:03:28 GMT

Is this a different paper to the original DeepMind video game paper? http://arxiv.org/abs/1312.5602

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by javierluraschi

Wed, 25 Feb 2015 15:09:02 GMT

Currently, it sees a board of 3x3 states, as in: _ _ G G B B _ _ G A next step would be to use real computer vision over a 3D camera in the environment aligned to R2D@ and a deep neural network to interpret pixels instead of states. DeepMind has a paper describing this approach: http://arxiv.org/pdf/1312.5602.pdf

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by modeless

Sun, 18 Jan 2015 05:53:04 GMT

The speech recognition and synthesis are primitive compared to any smartphone assistant these days. The natural language processing is about equivalent to SHRDLU from the 1960s [1]. It turns out that this approach based on manually constructing syntax trees and applying simple logic can make some fun demos but is ultimately a dead end in terms of making systems that are actually useful, as was discovered in the "AI winter". The part that controls Mario looks similar (if not identical) to this: http://aigamedev.com/open/interviews/mario-ai/ If you want to see the state of the art in using AI…

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — HN submission

Sat, 03 Jan 2015 20:03:01 GMT

Playing Atari with Deep Reinforcement Learning (2013) [pdf]

21 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by sinwave

Wed, 03 Dec 2014 01:07:07 GMT

While this complaint generally has validity, their paper [1] does IMO present an advance; it's not just handing a bunch of labeled data off to a large neural network. IIRC (forgive me, I read the paper a few weeks ago) the solution is at its core a reinforcement learning system, with the deep net only making up the component that predicts reward from a (state, action) pair. With that in hand, there remains the non-trivial RL problem of balancing "exploration vs exploitation" in learning good strategies to play the game(s). While NN's have been used in this capacity before, I believe that, as…

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by amoruso

Tue, 02 Dec 2014 22:48:24 GMT

Here's the original research paper if you're interested. http://arxiv.org/abs/1312.5602 I'll just quote their introduction instead of trying to summarize the paper: "Our goal is to create a single neural network agent that is able to successfully learn to play as many of the games as possible. The network was not provided with any game-specific information or hand-designed visual features, and was not privy to the internal state of the emulator; it learned from nothing but the video input, the reward and terminal signals, and the set of possible actions—just as a human player would.…

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by Sniffnoy

Tue, 21 Oct 2014 00:08:10 GMT

A note -- if you're linking to arXiv, it's better to link to the abstract (http://arxiv.org/abs/1312.5602) rather than directly to the PDF. From the abstract, one can easily click through to the PDF; not so the reverse. And the abstract allows one to do things like see different versions of the paper, search for other things by the same authors, etc.

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — HN submission

Mon, 20 Oct 2014 20:30:13 GMT

Playing Atari with Deep Reinforcement Learning [pdf]

37 points; 9 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by cyorir

Fri, 11 Jul 2014 18:27:50 GMT

I like this one because it is easier to get an idea of what the layout of the neural network itself is, and gives more control. Off the topic of neural networks in javascript but on the topic of neural networks in general, the readme links a cool paper on applying convolutional neural networks to old games. http://arxiv.org/abs/1312.5602

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by jkldotio

Tue, 11 Feb 2014 10:50:59 GMT

It's worth pointing out Google just bought the startup with the guys who wrote the "Playing Atari with Deep Reinforcement Learning" paper which is supposedly just an algorithm working on the raw pixels and then beating all other programs and half of the human experts.[1] [1] http://arxiv.org/pdf/1312.5602v1.pdf

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — HN submission

Tue, 28 Jan 2014 07:13:41 GMT

Deep Mind's neural networks play 7 Atari 2600 games with more skill than a human

5 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by jgalt212

Tue, 28 Jan 2014 03:12:40 GMT

beating the 2600 via AI is worth $500M, so beating Nintendo should be worth around $2B. http://arxiv.org/pdf/1312.5602v1.pdf

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by amaks

Mon, 27 Jan 2014 19:00:48 GMT

Exactly. Interesting, Yann LeCun in his G+ post (https://plus.google.com/u/0/+YannLeCunPhD/posts/LnKBPi9cCWm) explicitly mentioned that the acquired ML scientists have been focused in reinforcement learning. Also, they have published ArXiv paper on the subject: http://arxiv.org/pdf/1312.5602v1.pdf.

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — mentioned by karpathy

Mon, 27 Jan 2014 01:24:31 GMT

I remember that they had an impressive demo at the NIPS Deep Learning Workshop in December (probably a highlight for me and a few people I talked to afterwards) of a reinforcement learning agent playing Atari 2600 Games where the input consisted of an image that was fed through a Convolutional Neural Network. There is a paper on Arxiv that describes the approach ("Playing Atari with Deep Reinforcement Learning"[0]) but unfortunately I don't think they made the videos available. Deep Mind has a whole bunch of talented and serious people so this is an exciting acquisition. [0]…

Paper and discussion history. A mention is not an endorsement.

Playing Atari with Deep Reinforcement Learning — HN submission

Mon, 13 Jan 2014 20:14:03 GMT

Playing Atari with Deep Reinforcement Learning

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.