This paper proposed three new reinforcement learning tasks which involved dealing with images.

- Task 1: An agent crawls across a hidden image, revealing portions of it at each step. It must classify the image in the minimum amount of steps. For example classify the image as a cat after choosing to travel across the ears.
- Task 2: The agent crawls across a visible image to sit on it's target. For example a cat in a scene of pets.
- Task 3: The agent plays an Atari game where the background has been replaced with a distracting video.

These tasks are easy to construct, but solving them requires large scale visual processing or attention, which typically require deep networks. To address these new tasks, popular RL agents (PPO, A2C, and ACKTR) were augmented with a deep image processing network (ResNet-18), but they still performed poorly.

This paper performs a fascinating toy experiment, to try to see if something language-like in structure can be effectively induced in a population of agents, if they are given incentives that promote it. In some sense, a lot of what they find “just makes sense,” but it’s still a useful proof of concept to show that it can be done. 

The experiment they run takes place in a simple, two-dimensional world, with a fixed number of landmarks (representing locations goals need to take place), and agents, and actions. In this construction, each agent has a set of internal goals, which can either be actions (like “go to green landmark”) they themselves need to perform, or actions that they want another agent to perform. Agents’ goals are not visible to other agents, but all agents’ reward is defined to be the aggregated reward of all agents together, so if agent A has a goal involving an action of agent B’s, it’s in B’s “interest” to do that action, if it can be communicated to them. In order to facilitate other agents performing goals, at each step, each agent both takes an action, and also emits an “utterance”, which is just a discrete symbolic “word” out of some some fixed vocabulary of words (Note that applying “word” here is a but fuzzy; the agents do not pronounce or spell a character-based word, they just pick a discrete symbol that is playing the role of a word”. Even though other agents cannot see a given agent’s goals, they can see its public utterances, and so agents learn that communication is a way to induce other agents to perform desired actions. 

As a mathematically interesting aside: this setup, of allowing each agent to sample a single discrete word out of a small vocabulary at each setting, takes the deployment of some interesting computational tricks to accomplish. First off, in general, sampling a discrete single symbol out of a set of possible symbols is not differentiable, since it’s a discrete rather than continuous action, and derivatives require continuous functions. However, a paper from 2016 proposed a (heuristic) solution to this problem by means of the Gumbel Softmax Trick. This derives from the older “Gumbel Max Trick”, which is the mathematical fact that if you want to sample from a categorical distribution, a computationally easy way to do so is to add a variable sampled from a (0,1) Gumbel distribution to the log probability of each category, and then take the argmax of this as the index of the sample category (I’m not going to go another level down into why this is true, since I think it’s too far afield of the scope of this summary). Generally, argmax functions are also not differentiable. However, they can be approximated with softmaxes, which interpolate between a totally uniform and very nearly discrete-sample distribution based on a temperature parameter. In practice, or, at least, if this paper does what the original Gumbel Softmax paper did, during training, a discrete sample is taken, but a low-temperature continuous approximation is used for actual gradient calculation (i.e. for gradients, the model pretends that it used the continuous approximation rather than the discrete sample). 

https://i.imgur.com/0RpRJG2.png

Coming back to the actual communication problem, the authors do find that under these (admittedly fairly sanitized and contrived) circumstances, agents use series of discrete symbols to communicate goals to other agents, which ends up looking a lot like a very simple language. 

https://i.imgur.com/ZF0EbN4.png

As one might expect, in environments where there were only two agents, there was no symbol that ended up corresponding to “red agent” or “blue agent”, since each could realize that the other was speaking to it. However, in three-agent environments, the agents did develop symbols that clearly mapped to these categories, to specify who directions were being given to. The authors also tried cutting off verbal communication; in these situations, the agents used gaze and movement to try to signal what they wanted other agents to do. Probably most entertainingly, when neither verbal nor visual communication was allowed, agents would move to and “physically” push other agents to the location where their action needed to be performed. 

This paper continues in the tradition of curiosity-based models, which try to reward models for exploring novel parts of their environment, in the hopes this can intrinsically motivate learning. However, this paper argues that it’s insufficient to just treat novelty as an occasional bonus on top of a normal reward function, and that instead you should figure out a process that’s more specifically designed to increase novelty. Specifically: you should design a policy whose goal is to experience transitions and world-states that are high novelty. 

In this setup, like in other curiosity-based papers, “high novelty” is defined in terms of a state being unpredictable given a prior state, history, and action. However, where other papers saw novelty reward as something only applied when the agent arrived at somewhere novel, here, the authors build a model (technically, an ensemble of models) to predict the state at various future points. The ensemble is important here because it’s (quasi) bootstrapped, and thus gives us a measure of uncertainty. States where the predictions of the ensemble diverge represent places of uncertainty, and thus of high value to explore. I don’t 100% follow the analytic specification of this idea (even though the heuristic/algorithmic description makes sense). The authors frame the Utility function of a state and action as being equivalent to the Jenson Shannon Divergence (~distance between probability distributions) shown below. 

https://i.imgur.com/YIuomuP.png


Here, P(S | S, a, T) is the probability of a state given prior state and action under a given model of the environment (Transition Model), and P(gamma) is the distribution over the space of possible transition models one might learn. A “model” here is one network out of the ensemble of networks that makes up our bootstrapped (trained on different sets) distribution over models. Conceptually, I think this calculation is measuring “how different is each sampled model/state distribution from all the other models in the distribution over possible models”. If the models within the distribution diverge from one another, that indicates a location of higher uncertainty. 

What’s important about this is that, by building a full transition model, the authors can calculate the expected novelty or “utility” of future transitions it might take, because it can make a best guess based on this transition model (which, while called a “prior”, is really something trained on all data up to this current iteration). My understanding is that these kinds of models function similarly to a Q(s,a) or V(s) in a pure-reward case: they estimate the “utility reward” of different states and actions, and then the policy is updated to increase that expected reward. 

I’ve recently read papers on ICM, and I was a little disappointed that this paper didn’t appear to benchmark against that, but against Bootstrapped DQN and Exploration Bonus DQN, which I know less well and can less speak to the conceptual differences from this approach. Another difficulty in actually getting a good sense of results was that the task being tested on is fairly specific, and different from RL results coming out of the world of e.g. Atari and Deep Mind Labs. All of that said, this is a cautiously interesting idea, if the results generate to beat more baselines on more environments. 

This paper proposes a new curiosity-based intrinsic reward technique that seeks to address one of the failure modes of previous curiosity methods. The basic idea of curiosity is that, often, exploring novel areas of an environment can be correlated with gaining reward within that environment, and that we can find ways to incentivize the former that don’t require a hand-designed reward function. This is appealing because many useful-to-learn environments either lack inherent reward altogether, or have reward that is very sparse (i.e. no signal until you reach the end, at which point you get a reward of 1). In both of these cases, supplementing with some kind of intrinsic incentive towards exploration might improve performance. The existing baseline curiosity technique is called ICM, and works based on “surprisal”: asking the agent to predict the next state as a function of its current state, and incentivizing exploration of areas where the gap between these two quantities is high, to promote exploration of harder-to-predict (and presumably more poorly sampled) locations. However, one failure mode of this approach is something called the “noisy TV” problem, whereby if the environment contains something analogous to a television where one can press a button and go to a random channel, that is highly unpredictable, and thus a source of easy rewards, and thus liable to distract the agent from any other actions. 

As an alternative, the authors here suggest a different way of defining novelty: rather than something that is unpredictable, novelty should be seen as something far away from what I as an agent have seen before. This is more direct than the prior approach, which takes ‘hard to predict’ as a proxy for ‘somewhere I haven’t explored’, which may not necessary be a reasonable assumption. 

https://i.imgur.com/EfcAOoI.png

They implement this idea by keeping a memory of past (embedded) observations that the agent has seen during this episode, and, at each step, check whether the current observation is predicted to be more than K steps away than any of the observations in memory (more on that in a moment). If so, a bonus reward is added, and this observation is added to the aforementioned memory. (Which, waving hands vigorously, kind of ends up functioning as a spanning set of prior experience). 

https://i.imgur.com/gmHE11s.png

The question of “how many steps is observation A from observation B” is answered by a separate Comparator network which is trained in pretty straightforward fashion: a random-samplling policy is used to collect trajectories, which are then turned into pairs of observations as input, and a 1 if they occurred > k + p steps apart, and a 0 if they occurred < k steps apart. Then, these paired states are passed into a shared-weight convolutional network, which creates an embedding, and, from that embedding, a prediction is made as to whether they’re closer than the thresholds or farther away. This network is pre-trained before the actual RL training starts. (Minor sidenote: at RL-training time, the network is chopped into two, and the embedding read out and stored, and then input as a pair with each current observation to make the prediction). 

https://i.imgur.com/1oUWKyb.png

Overall, the authors find that their method works better than both ICM and no-intrinsic-reward for VizDoom (a maze + shooting game), and the advantage is stronger in situations more sparse settings of the external reward. 

https://i.imgur.com/4AURZbX.png

On DeepMind Lab tasks, they saw no advantage on tasks with already-dense extrinsic rewards, and little advantage on the “normally sparse”, which they suggest may be due to it actually being easier than expected. They added doors to a maze navigation task, to ensure the agent couldn’t find the target right away, and this situation brought better performance of their method. They also tried a fully no-extrinsic-reward situation, and their method strongly performed both the ICM baseline and (obviously) the only-extrinsic-reward baseline, which was basically an untrained random policy in this setting. Regarding the poor performance of the ICM baseline in this environment, “we hypothesise that the agent can most significantly change its current view when it is close to the wall — thus increasing one-step prediction error — so it tends to get stucknear “interesting” diverse textures on the walls.”. 

I really enjoyed this paper - in addition to being a clean, fundamentally empirical work, it was also clearly written, and had some pretty delightful moments of quotable zen, which I’ll reference at the end. The paper’s goal is to figure out how far curiosity-driven learning alone can take reinforcement learning systems, without the presence of an external reward signal. “Intrinsic” reward learning is when you construct a reward out of internal, inherent features of the environment, rather than using an explicit reward function. In some ways, intrinsic learning in RL can be thought of as analogous to unsupervised learning in classification problems, since reward functions are not inherent to most useful environments, and (when outside of game environments that inherently provide rewards), frequently need to be hand-designed. Curiosity-driven learning is a subset of intrinsic learning, which uses as a reward signal the difference between a prediction made by the dynamics model (predicting next state, given action) and the true observed next state. Situations where the this prediction area are high generate high reward for the agent, which incentivizes it to reach those states, which allows the dynamics model to then make ever-better predictions about them. 

Two key questions this paper raises are: 


1) Does this approach even work when used on it’s own? Curiosity had previously most often been used as a supplement to extrinsic rewards, and the authors wanted to know how far it could go separately. 


2) What is the best feature to do this “surprisal difference” calculation in? Predicting raw pixels is a high-dimensional and noisy process, so naively we might want something with fewer, more informationally-dense dimensions, but it’s not obvious which methods that satisfy these criteria will work the best, so the paper empirically tried them. 

The answer to (1) seems to be: yes, at least in the video games tested. Impressively, when you track against extrinsic reward (which, again, these games have, but we’re just ignoring in a curiosity-only setting), the agents manage to increase it despite not optimizing against it directly. There were some Atari games where this effect was stronger than others, but overall performance was stronger than might have been naively expected. One note the authors made, worth keeping in mind, is that it’s unclear how much of this is an artifact of the constraints and incentives surrounding game design, which might reflect back a preference for gradually-increasing novelty because humans find it pleasant. 

https://i.imgur.com/zhl39vo.png

As for (2), another interesting result of this paper is that random features performed consistently well as a feature space to do these prediction/reality comparisons in. Random features here is really just as simple as “design a convolutional net that compresses down to some dimension, randomly initialize it, and then use those randomly initialized weights to run forward passes of the network to get your lower-dimensional state”. This has the strong disadvantage of (presumably) not capturing any meaningful information about the state, but also has the advantage of being stable: the other techniques tried, like pulling out the center of a VAE bottleneck, changed over time as they were being trained on new states, so they were informative, but non-stationary. 

My two favorite quotable moments from this paper were: 
1) When the authors noted that they had removed the “done” signal associated with an agent “dying,” because it is itself a sort of intrinsic reward. However, “in practice, we do find that the agent avoids dying in the games since that brings it back to the beginning of the game, an area it has already seen many times and where it can predict the dynamics well.”. Short and sweet: “Avoiding death, because it’s really boring” 

https://i.imgur.com/SOfML8d.png

2) When they noted that an easy way to hack the motivation structure of a curiosity-driven agent was through a “noisy tv”, which, every time you pressed the button, jumped to a random channel. As expected, when they put this distraction inside a maze, the agent spent more time jacking up reward through that avenue, rather than exploring. Any resemblance to one’s Facebook feed is entirely coincidental.