This list is big compilation of all things trying to adapt Reinforcement Learning techniques in real world.Whether it's mixing real world data into mix or trying to adapt simulations in a better way.It will also include some of Imitation Learning and Meta Learning along the way. If you have anything missing feel free to open a PR, I'm all for community contributions. I'm open to new categories so just read the contributing doc and provide a pull request. You can help also by starring our lovely repository and sharing 3 be safe! Any academic work done related to RL in real world.This is the other part of list, anything doesn't fit but still related gets here.

Configuring databases for efficient querying is a complex task, often carried out by a database administrator. Solving the problem of building indexes that truly optimize database access requires a substantial amount of database and domain knowledge, the lack of which often results in wasted space and memory for irrelevant indexes, possibly jeopardizing database performance for querying and certainly degrading performance for updating. We develop an architecture to solve the problem of automatically indexing a database by using reinforcement learning to optimize queries by indexing data throughout the lifetime of a database. In our experimental evaluation, our architecture shows superior performance compared to related work on reinforcement learning and genetic algorithms, maintaining near-optimal index configurations and efficiently scaling to large databases.

The current reward learning from human preferences could be used for resolving complex reinforcement learning (RL) tasks without access to the reward function by defining a single fixed preference between pairs of trajectory segments. However, the judgement of preferences between trajectories is not dynamic and still requires human inputs over 1,000 times. In this study, we propose a human preference scaling model that naturally reflects the human perception of the degree of choice between trajectories and then develop a human-demonstration preference model via supervised learning to reduce the number of human inputs. The proposed human preference scaling model with demonstrations can effectively solve complex RL tasks and achieve higher cumulative rewards in simulated robot locomotion - MuJoCo games - relative to the single fixed human preferences. Furthermore, our developed human-demonstration preference model only needs human feedback for less than 0.01\% of the agent's interactions with the environment and significantly reduces up to 30\% of the cost of human inputs compared to the existing approaches. To present the flexibility of our approach, we released a video (https://youtu.be/jQPe1OILT0M) showing comparisons of behaviours of agents trained with different types of human inputs. We believe that our naturally inspired human preference scaling with demonstrations is beneficial for precise reward learning and can potentially be applied to state-of-the-art RL systems, such as autonomy-level driving systems.

Despite recent advances in artificial intelligence (AI) research, human children are still by far the best learners we know of, learning impressive skills like language and high-level reasoning from very little data. Children's learning is supported by highly efficient, hypothesis-driven exploration: in fact, they explore so well that many machine learning researchers have been inspired to put videos like the one below in their talks to motivate research into exploration methods. However, because applying results from studies in developmental psychology can be difficult, this video is often the extent to which such research actually connects with human cognition. Why is directly applying research from developmental psychology to problems in AI so hard? For one, taking inspiration from developmental studies can be difficult because the environments that human children and artificial agents are typically studied in can be very different.

Intrinsically motivated spontaneous exploration is a key enabler of autonomous lifelong learning in human children. It enables the discovery and acquisition of large repertoires of skills through self-generation, self-selection, self-ordering and self-experimentation of learning goals. We present an algorithmic approach called Intrinsically Motivated Goal Exploration Processes (IMGEP) to enable similar properties of autonomous or self-supervised learning in machines. The IMGEP algorithmic architecture relies on several principles: 1) self-generation of goals, generalized as fitness functions; 2) selection of goals based on intrinsic rewards; 3) exploration with incremental goal-parameterized policy search and exploitation of the gathered data with a batch learning algorithm; 4) systematic reuse of information acquired when targeting a goal for improving towards other goals. We present a particularly efficient form of IMGEP, called Modular Population-Based IMGEP, that uses a population-based policy and an object-centered modularity in goals and mutations. We provide several implementations of this architecture and demonstrate their ability to automatically generate a learning curriculum within several experimental setups including a real humanoid robot that can explore multiple spaces of goals with several hundred continuous dimensions. While no particular target goal is provided to the system, this curriculum allows the discovery of skills that act as stepping stone for learning more complex skills, e.g. nested tool use. We show that learning diverse spaces of goals with intrinsic motivations is more efficient for learning complex skills than only trying to directly learn these complex skills.

The size and quality of chemical libraries to the drug discovery pipeline are crucial for developing new drugs or repurposing existing drugs. Existing techniques such as combinatorial organic synthesis and High-Throughput Screening usually make the process extraordinarily tough and complicated since the search space of synthetically feasible drugs is exorbitantly huge. While reinforcement learning has been mostly exploited in the literature for generating novel compounds, the requirement of designing a reward function that succinctly represents the learning objective could prove daunting in certain complex domains. Generative Adversarial Network-based methods also mostly discard the discriminator after training and could be hard to train. In this study, we propose a framework for training a compound generator and learning a transferable reward function based on the entropy maximization inverse reinforcement learning paradigm. We show from our experiments that the inverse reinforcement learning route offers a rational alternative for generating chemical compounds in domains where reward function engineering may be less appealing or impossible while data exhibiting the desired objective is readily available.

The Predictive Information is the mutual information between the past and the future, I(X_past; X_future). We hypothesize that capturing the predictive information is useful in RL, since the ability to model what will happen next is necessary for success on many tasks. To test our hypothesis, we train Soft Actor-Critic (SAC) agents from pixels with an auxiliary task that learns a compressed representation of the predictive information of the RL environment dynamics using a contrastive version of the Conditional Entropy Bottleneck (CEB) objective. We refer to these as Predictive Information SAC (PI-SAC) agents. We show that PI-SAC agents can substantially improve sample efficiency over challenging baselines on tasks from the DM Control suite of continuous control environments. We evaluate PI-SAC agents by comparing against uncompressed PI-SAC agents, other compressed and uncompressed agents, and SAC agents directly trained from pixels.

"Nonstationarity" is a fundamental problem in cooperative multi-agent reinforcement learning (MARL)--each agent must relearn information about the other agent's policies due to the other agents learning, causing information to "ring" between agents and convergence to be slow. The MAILP model, introduced by Terry and Grammel (2020), is a novel model of information transfer during multi-agent learning. We use the MAILP model to show that increasing training centralization arbitrarily mitigates the slowing of convergence due to nonstationarity. The most centralized case of learning is parameter sharing, an uncommonly used MARL method, specific to environments with homogeneous agents, that bootstraps a single-agent reinforcement learning (RL) methods and learns an identical policy for each agent. We experimentally replicate the result of increased learning centralization leading to better performance on the MARL benchmark set from Gupta et al. (2017). We further apply parameter sharing to 8 "more modern" single-agent deep RL (DRL) methods for the first time in the literature. With this, we achieved the best documented performance on a set of MARL benchmarks and achieved up to 44 times more average reward in as little as 16% as many episodes compared to documented parameter sharing arrangement. We finally offer a formal proof of a set of methods that allow parameter sharing to serve in environments with heterogeneous agents.

Distributional reinforcement learning (RL) has achieved state-of-the-art performance in Atari games by recasting the traditional RL into a distribution estimation problem, explicitly estimating the probability distribution instead of the expectation of a total return. The bottleneck in distributional RL lies in the estimation of this distribution where one must resort to an approximate representation of the return distributions which are infinite-dimensional. Most existing methods focus on learning a set of predefined statistic functionals of the return distributions requiring involved projections to maintain the order statistics. We take a different perspective using deterministic sampling wherein we approximate the return distributions with a set of deterministic particles that are not attached to any predefined statistic functional, allowing us to freely approximate the return distributions. The learning is then interpreted as evolution of these particles so that a distance between the return distribution and its target distribution is minimized. This learning aim is realized via maximum mean discrepancy (MMD) distance which in turn leads to a simpler loss amenable to backpropagation. Experiments on the suite of Atari 2600 games show that our algorithm outperforms the standard distributional RL baselines and sets a new record in the Atari games for non-distributed agents.

Standard reinforcement learning (RL) aims to find an optimal policy that identifies the best action for each state. However, in healthcare settings, many actions may be near-equivalent with respect to the reward (e.g., survival). We consider an alternative objective -- learning set-valued policies to capture near-equivalent actions that lead to similar cumulative rewards. We propose a model-free algorithm based on temporal difference learning and a near-greedy heuristic for action selection. We analyze the theoretical properties of the proposed algorithm, providing optimality guarantees and demonstrate our approach on simulated environments and a real clinical task. Empirically, the proposed algorithm exhibits good convergence properties and discovers meaningful near-equivalent actions. Our work provides theoretical, as well as practical, foundations for clinician/human-in-the-loop decision making, in which humans (e.g., clinicians, patients) can incorporate additional knowledge (e.g., side effects, patient preference) when selecting among near-equivalent actions.