- *issue:* RL on real systems -> sparse and slow data sampling;
- *solution:* pre-train the agent with the EGAN;
- *performance:* ~20% improvement of training time in the beginning of learning compared to no pre-training; ~5% improvement and smaller variations compared to GAN pre-training.

## Introduction

5G telecom systems -> fufill ultra-low latency, high robustness, quick response to changed capacity needs, and dynamic allocation of functionality.

*Problems:*

1. exploration has an impact on the service quality in real-time service systems;
2. sparse and slow data sampling -> extended training duration.

## Enhanced GAN

**Fomulas**

the training data for RL tasks:

$$x = [x_1, x_2] = [(s_t,a),(s_{t+1},r)]$$

the generated data:

$$G(z) = [G_1(z), G_2(z)] =  [(s'_t,a'),(s'_{t+1},r')] $$

the value function for GAN:

$$V(D,G) = \mathbb{E}_{z \sim p_z(z)}[\log(1-D(G(z)))] + \lambda D_{KL}(P||Q)$$

where the regularization term $D_{KL}$ has the following form:

$$D_{KL}(P||Q) = \sum_i P(i) \log \frac{P(i)}{Q(i)}$$

**EGAN structure**

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

**Algorithm**

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

The enhancer is fed with training data *D\_r(s\_t, a)* and *D\_r(s\_{t+1}, r)*, and trained by supervised learning. After GAN generates synthetic data *D\_t(s\_t, a, s\_{t+1}, r)*, the enhancer could enhance the dependency between *D\_t(s\_t, a)* and *D\_t(s\_{t+1}, r)* and update the weights of GAN.

## Results

two lines of experiments on CartPole environment involved with PG agents: 

1. one for comparing the learning curves of agents with no pre-training, GAN pre-training and EGAN pre-training. => Result: EGAN > GAN > no pre-training

2. one for comparing the learning curves of agents with EGAN pre-training for various episodes (500, 2000, 5000). => Result: 5000 > 2000 ~= 500

They incorporate fMRI features into POS tagging, under the assumption that reading semantically/functionally different words will activate the brain in different ways. For this they use a dataset of fMRI recordings, where the subjects were reading a chapter of Harry Potter. The main issue is that fMRI has very low temporal resolution – there is only one fMRI reading per 4 tokens, and in general it takes around 4-14 seconds for something to show up in fMRI. Nevertheless, they construct token-level vectors by using a Gaussian weighted average, integrate them into an unsupervised POS tagger, and show that it is able to improve performance.

https://i.imgur.com/TU60N6w.png

A model for document sentiment classification which can also return sentence-level sentiment predictions. They construct sentence-level representations using a convnet, use this to predict a sentence-level probability distribution over possible sentiment labels, and then combine these over all sentences either with a fixed weight vector or using an attention mechanism. They release a new dataset of 200 documents annotated on the level of sentences and discourse units.

https://i.imgur.com/A6YpmLU.png

Aim: generate realistic-looking synthetic data that can be used to train 3D Human Pose Estimation methods. Instead of rendering 3D models, they choose to combine parts of real images.

Input: RGB images with 2D annotations + a query 3D pose.
Output: A synthetic image, stitched from patches of the images, so that it looks like a person in the query 3D pose.

Steps:
- Project 3D pose on random camera to get 2D coords
- For each joint, find an image in the 2D annotated dataset whose annotation is locally similar
- Based on the similarities, decide for each pixel which image is most relevant.
- For each pixel, take the histogram of the chosen images in a neighborhood, and use this as blending factors to generate the result.

They also present a method that they trained on this synthetic dataset.

# Keypoints
- Proposes the HIerarchical Reinforcement learning with Off-policy correction (**HIRO**) algorithm.
 - Does not require careful task-specific design.
 - Generic goal representation to make it broadly applicable, without any manual design of goal spaces, primitives, or controllable dimensions.
- Use of off-policy experience using a novel off-policy correction.
- A two-level hierarchy architecture
 - A higher-level controller outputs a goal for the lower-level controller every **c** time steps and collects the rewards given by the environment, being the goal the desired change in state space
 - The lower level controller has the goal given added to its input and acts directly in the environment, the reward received is parametrized from the current state and the goal.

# Background
This paper adopts a standard continuous control reinforcement learning setting, in which an agent acts on an environment that yields a next state and a reward from unknown functions. This paper utilizes the TD3 learning algorithm.

## General and Efficient Hierarchical Reinforcement Learning

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

## Hierarchy of Two Policies

The higher-level policy $\mu^{hi}$ outputs a goal $g_t$, which correspond directly to desired relative changes in state that the lower-level policy $\mu^{lo}$ attempts to reach. $\mu^{hi}$ operates at a time abstraction, updating the goal $g_t$ and collecting the environment rewards $R_t$ every $c$ environment steps, the higher-level transition $(s_{t:t+c−1},g_{t:t+c−1},a_{t:t+c−1},R_{t:t+c−1},s_{t+c})$ is stored for off-policy training.

The lower-level policy $\mu^{lo}$ outputs an action to be applied directly to the environment, having as input the current environment observations $s_t$ and the goal $g_t$. The goal  $g_t$ is given by $\mu^{hi}$ every $c$ environment time steps, for the steps in between, the goal $g_t$ used by $\mu^{lo}$ is given by the transition function $g_t=h(s_{t−1},g_{t−1},s_t)$, the lower-level controller reward is provided by the parametrized reward function $r_t=r(s_t,g_t,a_t,s_{t+1})$.  The  lower-level  transition $(s_t,g_t,a_t,r_t,s_{t+1}, g_{t+1})$ is stored for off-policy training.

## Parameterized Rewards

The goal $g_t$ indicates a desired relative changes in state observations, the lower-level agent task is to take actions from state $s_t$ that yield it an observation $s_{t+c}$ that is close to $s_t+g_t$. To maintain the same absolute position of the goal regardless of state change, the goal transition model, used between $\mu^{hi}$ updates every $c$ steps, is defined as:

$h(s_t,g_t,s_{t+1}) =s_t+g_t−s_{t+1}$

And the reward given to the lower-level controller is defined as to reinforce reaching a state closer to the goal $g_t$, this paper parametrizes it by the function:
$r(s_t,g_t,a_t,s_{t+1}) =−||s_t+g_t−s_{t+1}||_2$.

## Off-Policy Corrections for Higher-Level Training

The higher-level transitions stored $(s_{t:t+c−1},g_{t:t+c−1},a_{t:t+c−1},R_{t:t+c−1},s_{t+c})$ have to be converted to state-action-reward transitions $(s_t,g_t,∑R_{t:t+c−1},s_{t+c})$ as they can be used in standard off-policy RL algorithms, however, since the lower-level controller is evolving, these past transitions do not accurately represent the actions tha would be taken by the current lower-level policy and must be corrected.

This paper correction technique used is to change the goal $g_t$ of past transitions using an out of date lower-level controller to a relabeled goal $g ̃_t$ which is likely to induce the same lower-level behavior with the updated $\mu^{lo}$. In other words, we want to find a goal $g ̃_t$ which maximizes the probability $μ_{lo}(a_{t:t+c−1}|s_{t:t+c−1},g ̃_{t:t+c−1})$, in which the $\mu^{lo}$ is the current policy and the actions $a_{t:t+c−1}$ and states $s_{t:t+c−1}$ are from the stored high level transition.

To approximately maximize this quantity in practice, the authors calculated the probability for 10 candidates $g ̃_t$, eight candidate goals sampled randomly from a Gaussian centered at $s_{t+c}−s_t$, the original goal $g_t$ and a goal corresponding to the difference $s_{t+c}−s_t$.

# Experiments
https://i.imgur.com/iko9nCd.png

https://i.imgur.com/kGx8fZv.png

The authors compared the $HIRO$ method to prior method in 4 different environments:
- Ant Gather;
- Ant Maze;
- Ant Push;
- Ant Fall.

They also performed an ablative analysis with the following variants:
- With lower-level re-labeling;
- With pre-training;
- No off-policy correction;
- No HRL.

# Closing Points
- The method proposed is interesting in the hierarchical reinforcement learning setting for not needing a specific design, the generic goal representation enables applicability without the need of designing a goal space manually;
- The off-policy correction method enables this algorithm to be sample efficient;
- The hierarchical structure with intermediate goals on state-space enables to better visualize the agent goals;
- The paper Appendix elaborates on possible alternative off-policy corrections.