Related papers: Improvements on Hindsight Learning
Standard computer vision systems assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself. We address the problem of learning to…
Model-based next state prediction and state value prediction are slow to converge. To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which…
One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions. Designing such reward functions is difficult in part because the user only has an implicit understanding of the task…
One of the key reasons for the high sample complexity in reinforcement learning (RL) is the inability to transfer knowledge from one task to another. In standard multi-task RL settings, low-reward data collected while trying to solve one…
Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must learn to generate programs for diverse scenes conditioned on a…
Learning a goal-oriented dialog policy is generally performed offline with supervised learning algorithms or online with reinforcement learning (RL). Additionally, as companies accumulate massive quantities of dialog transcripts between…
Recommending a sequence of activities for an ongoing case requires that the recommendations conform to the underlying business process and meet the performance goal of either completion time or process outcome. Existing work on next…
This research focuses on enhancing reinforcement learning (RL) algorithms by integrating penalty functions to guide agents in avoiding unwanted actions while optimizing rewards. The goal is to improve the learning process by ensuring that…
Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising…
Recent progress in deep reinforcement learning (RL) and computer vision enables artificial agents to solve complex tasks, including locomotion, manipulation and video games from high-dimensional pixel observations. However, domain specific…
The performance of reinforcement learning depends upon designing an appropriate action space, where the effect of each action is measurable, yet, granular enough to permit flexible behavior. So far, this process involved non-trivial user…
Fictitious play with reinforcement learning is a general and effective framework for zero-sum games. However, using the current deep neural network models, the implementation of fictitious play faces crucial challenges. Neural network model…
Actor critic methods with sparse rewards in model-based deep reinforcement learning typically require a deterministic binary reward function that reflects only two possible outcomes: if, for each step, the goal has been achieved or not. Our…
Hierarchical Reinforcement Learning (HRL) exploits temporally extended actions, or options, to make decisions from a higher-dimensional perspective to alleviate the sparse reward problem, one of the most challenging problems in…
Reinforcement Learning has suffered from poor reward specification, and issues for reward hacking even in simple enough domains. Preference Based Reinforcement Learning attempts to solve the issue by utilizing binary feedbacks on queried…
Experience replay \citep{lin1993reinforcement, mnih2015human} is a widely used technique to achieve efficient use of data and improved performance in RL algorithms. In experience replay, past transitions are stored in a memory buffer and…
Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various exploration actions before…
Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that…
An important problem in reinforcement learning is designing agents that learn to solve tasks safely in an environment. A common solution is for a human expert to define either a penalty in the reward function or a cost to be minimised when…
Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notable problem in training deep RL agents to…