A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
A method for setting up an automatic curriculum for reinforcement learning tasks.
Max entropy exploration guides reinforcement learning agents to pursue achievable goals.
Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for such tasks: model-free or model-based. Each of these approaches has limitations.…
New method learns optimal environment and goal difficulty for reinforcement learning.
We propose a novel framework for multi-task reinforcement learning (MTRL). Using a variational inference formulation, we learn policies that generalize across both changing dynamics and goals. The resulting policies are parametrized by shared parameters that allow for transfer between different dynamics and goal condit…
Sparse reward problems are one of the biggest challenges in Reinforcement Learning. Goal-directed tasks are one such sparse reward problems where a reward signal is received only when the goal is reached. One promising way to train an agent to perform goal-directed tasks is to use Hindsight Learning approaches. In thes…
PlanGAN uses GANs to plan efficient trajectories for multi-goal tasks in sparse reward environments.
We propose a novel framework to identify sub-goals useful for exploration in sequential decision making tasks under partial observability. We utilize the variational intrinsic control framework (Gregor et.al., 2016) which maximizes empowerment -- the ability to reliably reach a diverse set of states and show how to ide…
Improves reinforcement learning for complex tasks with sparse feedback.
All-goals updating exploits the off-policy nature of Q-learning to update all possible goals an agent could have from each transition in the world, and was introduced into Reinforcement Learning (RL) by Kaelbling (1993). In prior work this was mostly explored in small-state RL problems that allowed tabular representati…
Improves RL planning by proposing sub-goals hierarchically.
Causal reasoning has been an indispensable capability for humans and other intelligent animals to interact with the physical world. In this work, we propose to endow an artificial agent with the capability of causal reasoning for completing goal-directed tasks. We develop learning-based approaches to inducing causal kn…
C-Learning estimates reachability over time to solve multi-goal tasks.
Reinforcement learning algorithms use correlations between policies and rewards to improve agent performance. But in dynamic or sparsely rewarding environments these correlations are often too small, or rewarding events are too infrequent to make learning feasible. Human education instead relies on curricula--the break…
OptiGAN uses GAN and RL to optimize sequence generation for specific goals.
A new method for robot manipulation tasks using imagined object goals.
Agents need world models to generalize multi-step tasks.
Goal-oriented reinforcement learning has recently been a practical framework for robotic manipulation tasks, in which an agent is required to reach a certain goal defined by a function on the state space. However, the sparsity of such reward definition makes traditional reinforcement learning algorithms very inefficien…
This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.
GOIMDA selects inputs to maximize expected influence on a goal functional, reducing data acquisition needs.
Learning to solve complex goal-oriented tasks with sparse terminal-only rewards often requires an enormous number of samples. In such cases, using a set of expert trajectories could help to learn faster. However, Imitation Learning (IL) via supervised pre-training with these trajectories may not perform as well and gen…
Goal-conditioned policies are used in order to break down complex reinforcement learning (RL) problems by using subgoals, which can be defined either in state space or in a latent feature space. This can increase the efficiency of learning by using a curriculum, and also enables simultaneous learning and generalization…
LEXA learns to discover and achieve goals in unseen environments.
Eikonal-Constrained QRL improves goal-reaching in reinforcement learning.
Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and un…
In hierarchical reinforcement learning a major challenge is determining appropriate low-level policies. We propose an unsupervised learning scheme, based on asymmetric self-play from Sukhbaatar et al. (2018), that automatically learns a good representation of sub-goals in the environment and a low-level policy that can…
We explore the behavior of a standard convolutional neural net in a continual-learning setting that introduces visual classification tasks sequentially and requires the net to master new tasks while preserving mastery of previously learned tasks. This setting corresponds to that which human learners face as they acquir…
ADRL improves participant selection in MCS systems.
AMIGo uses adversarial intrinsic goals to teach RL agents new skills.
Reinforcement learning requires manual specification of a reward function to learn a task. While in principle this reward function only needs to specify the task goal, in practice reinforcement learning can be very time-consuming or even infeasible unless the reward function is shaped so as to provide a smooth gradient…
Study combines chit-chat and goal-oriented dialogue in fantasy games.
Transfer learning across different reinforcement learning (RL) tasks is becoming an increasingly valuable area of research. We consider a goal-based multi-task RL framework and mechanisms by which previously solved tasks can reduce sample complexity and regret when the agent is faced with a new task. Specifically, we i…
New RL framework learns task completion without prior knowledge.
Paper proposes a method to make learned models focus on task-relevant information.
Proposes Mv-TCNN for continual learning without known tasks in advance.
This work tackles long-term visual planning by goal-conditioned hierarchical predictors.
Biological intelligence can learn to solve many diverse tasks in a data efficient manner by re-using basic knowledge and skills from one task to another. Furthermore, many of such skills are acquired without explicit supervision in an intrinsically driven fashion. This is in contrast to the state-of-the-art reinforceme…
Director learns hierarchical behaviors from pixels, outperforming exploration methods.
Developing learning methods which do not discriminate subgroups in the population is a central goal of algorithmic fairness. One way to reach this goal is by modifying the data representation in order to meet certain fairness constraints. In this work we measure fairness according to demographic parity. This requires t…
USFs capture dynamics for faster RL task transfer.
A new EM framework for goal-conditioned RL improves performance on sparse reward tasks.
Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based algorithms use dynamics models and reward functions to achieve goals. Yet, reward functions that evoke desirable behavior are often difficul…
New RL approach infers optimal policies via variational inference.
Method distills reward and strategies from diverse demonstrators.
Rewriting history improves RL algorithms for solving multiple tasks.
In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected randomly for replay. However, the achieved goals in the replay buffer are often biase…
Reinforcement learning and planning methods require an objective or reward function that encodes the desired behavior. Yet, in practice, there is a wide range of scenarios where an objective is difficult to provide programmatically, such as tasks with visual observations involving unknown object positions or deformable…
AI bias arises from human-defined goals, not algorithmic flaws.