We propose a simple architecture for deep reinforcement learning by embedding inputs into a learned Fourier basis and show that it improves the sample efficiency of both state-based and image-based RL. We perform infinite-width analysis of our architecture using the Neural Tangent Kernel and theoretically show that tuning the initial variance of the Fourier basis is equivalent to functional regularization of the learned deep network. That is, these learned Fourier features allow for adjusting the degree to which networks underfit or overfit different frequencies in the training data, and hence provide a controlled mechanism to improve the stability and performance of RL optimization. Empirically, this allows us to prioritize learning low-frequency functions and speed up learning by reducing networks' susceptibility to noise in the optimization process, such as during Bellman updates. Experiments on standard state-based and image-based RL benchmarks show clear benefits of our architecture over the baselines. Website at https://alexanderli.com/learned-fourier-features

In these notes we will tackle the problem of finding optimal policies for Markov decision processes (MDPs) which are not fully known to us. Our intention is to slowly transition from an offline setting to an online (learning) setting. Namely, we are moving towards reinforcement learning. As a reminder, a (stationary) MDP M is a 4-tuple (S,A,P,r) where: - S is a finite set of states, - A is a finite set of actions. For intuition, this is just a graph-based way of saying that the reachable part of the Markov chain induced by the policy has a single closed communicating class. Let M be a communicating MDP and i one of its states.

Soft Actor-Critic (SAC) is considered the state-of-the-art algorithm in continuous action space settings. It uses the maximum entropy framework for efficiency and stability, and applies a heuristic temperature Lagrange term to tune the temperature $\alpha$, which determines how "soft" the policy should be. It is counter-intuitive that empirical evidence shows SAC does not perform well in discrete domains. In this paper we investigate the possible explanations for this phenomenon and propose Target Entropy Scheduled SAC (TES-SAC), an annealing method for the target entropy parameter applied on SAC. Target entropy is a constant in the temperature Lagrange term and represents the target policy entropy in discrete SAC. We compare our method on Atari 2600 games with different constant target entropy SAC, and analyze on how our scheduling affects SAC.

Model-based reinforcement learning methods achieve significant sample efficiency in many tasks, but their performance is often limited by the existence of the model error. To reduce the model error, previous works use a single well-designed network to fit the entire environment dynamics, which treats the environment dynamics as a black box. However, these methods lack to consider the environmental decomposed property that the dynamics may contain multiple sub-dynamics, which can be modeled separately, allowing us to construct the world model more accurately. In this paper, we propose the Environment Dynamics Decomposition (ED2), a novel world model construction framework that models the environment in a decomposing manner. ED2 contains two key components: sub-dynamics discovery (SD2) and dynamics decomposition prediction (D2P). SD2 discovers the sub-dynamics in an environment and then D2P constructs the decomposed world model following the sub-dynamics. ED2 can be easily combined with existing MBRL algorithms and empirical results show that ED2 significantly reduces the model error and boosts the performance of the state-of-the-art MBRL algorithms on various tasks.

We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations. Specifically, we propose a momentum-based decentralized policy gradient tracking (MDPGT) where a new momentum-based variance reduction technique is used to approximate the local policy gradient surrogate with importance sampling, and an intermediate parameter is adopted to track two consecutive policy gradient surrogates. Moreover, MDPGT provably achieves the best available sample complexity of $\mathcal{O}(N^{-1}\epsilon^{-3})$ for converging to an $\epsilon$-stationary point of the global average of $N$ local performance functions (possibly nonconcave). This outperforms the state-of-the-art sample complexity in decentralized model-free reinforcement learning, and when initialized with a single trajectory, the sample complexity matches those obtained by the existing decentralized policy gradient methods. We further validate the theoretical claim for the Gaussian policy function. When the required error tolerance $\epsilon$ is small enough, MDPGT leads to a linear speed up, which has been previously established in decentralized stochastic optimization, but not for reinforcement learning. Lastly, we provide empirical results on a multi-agent reinforcement learning benchmark environment to support our theoretical findings.

Single-agent reinforcement learning algorithms in a multi-agent environment are inadequate for fostering cooperation. If intelligent agents are to interact and work together to solve complex problems, methods that counter non-cooperative behavior are needed to facilitate the training of multiple agents. This is the goal of cooperative AI. Recent work in adversarial machine learning, however, shows that models (e.g., image classifiers) can be easily deceived into making incorrect decisions. In addition, some past research in cooperative AI has relied on new notions of representations, like public beliefs, to accelerate the learning of optimally cooperative behavior. Hence, cooperative AI might introduce new weaknesses not investigated in previous machine learning research. In this paper, our contributions include: (1) arguing that three algorithms inspired by human-like social intelligence introduce new vulnerabilities, unique to cooperative AI, that adversaries can exploit, and (2) an experiment showing that simple, adversarial perturbations on the agents' beliefs can negatively impact performance. This evidence points to the possibility that formal representations of social behavior are vulnerable to adversarial attacks.

In reinforcement learning, an artificial intelligence faces a game-like situation. The computer employs trial and error to come up with a solution to the problem. This is the most complete Reinforcement Learning course on Udemy. In it you will learn the basics of Reinforcement Learning, one of the three paradigms of modern artificial intelligence. You will implement from scratch adaptive algorithms that solve control tasks based on experience.

But instead of using TensorFlow, I've built a deep reinforcement learning framework using PyTorch. PyTorch is a deep learning framework for fast, flexible ...Reinforcement Learning with Pytorch All the code and installation instructions have been updated and verified to work with Pytorch 1.6!! Artificial Intelligence is dynamically edging its way into our lives. It is already broadly available and we use it - sometimes even not knowing it - on daily basis. Soon it will be our permanent, every day companion. And where can we place Reinforcement Learning in AI world?

In this paper, multi-agent reinforcement learning is used to control a hybrid energy storage system working collaboratively to reduce the energy costs of a microgrid through maximising the value of renewable energy and trading. The agents must learn to control three different types of energy storage system suited for short, medium, and long-term storage under fluctuating demand, dynamic wholesale energy prices, and unpredictable renewable energy generation. Two case studies are considered: the first looking at how the energy storage systems can better integrate renewable energy generation under dynamic pricing, and the second with how those same agents can be used alongside an aggregator agent to sell energy to self-interested external microgrids looking to reduce their own energy bills. This work found that the centralised learning with decentralised execution of the multi-agent deep deterministic policy gradient and its state-of-the-art variants allowed the multi-agent methods to perform significantly better than the control from a single global agent. It was also found that using separate reward functions in the multi-agent approach performed much better than using a single control agent. Being able to trade with the other microgrids, rather than just selling back to the utility grid, also was found to greatly increase the grid's savings.

Reinforcement Learning is an extremely cool and innovative branch of Machine Learning. Today, I'll be talking about how I replicated an existing Snake Game AI. The Snake Game has been built and coded millions of times. It's a pretty basic concept but I'll quickly explain for a little bit of context. I used pygame as my main module for building the display and features of the game.