Rishabh Agarwal

Au-delà de « Tabula Rasa » : l’apprentissage par renforcement réincarné (« RRL »)

Billets de blogue

Beyond Tabula Rasa: Reincarnating Reinforcement Learning

25 novembre 2022

par

Max Schwarzer

Rishabh Agarwal

Lire l'article

Publications

Bootstrapped Representations in Reinforcement Learning

Charline Le Lan

Stephen Tu

Mark Rowland

Anna Harutyunyan

Will Dabney

In reinforcement learning (RL), state representations are key to dealing with large or continuous state spaces. While one of the promises of… (voir plus) deep learning algorithms is to automatically construct features well-tuned for the task they try to solve, such a representation might not emerge from end-to-end training of deep RL agents. To mitigate this issue, auxiliary objectives are often incorporated into the learning process and help shape the learnt state representation. Bootstrapping methods are today's method of choice to make these additional predictions. Yet, it is unclear which features these algorithms capture and how they relate to those from other auxiliary-task-based approaches. In this paper, we address this gap and provide a theoretical characterization of the state representation learnt by temporal difference learning (Sutton, 1988). Surprisingly, we find that this representation differs from the features learned by Monte Carlo and residual gradient algorithms for most transition structures of the environment in the policy evaluation setting. We describe the efficacy of these representations for policy evaluation, and use our theoretical analysis to design new auxiliary learning rules. We complement our theoretical results with an empirical comparison of these learning rules for different cumulant functions on classic domains such as the four-room domain (Sutton et al, 1999) and Mountain Car (Moore, 1990).

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (publié)

A Novel Stochastic Gradient Descent Algorithm for LearningPrincipal Subspaces

Charline Le Lan

Joshua Greaves

Jesse Farebrother

Mark Rowland

Fabian Pedregosa

In this paper, we derive an algorithm that learns a principal subspace from sample entries, can be applied when the approximate subspace i… (voir plus)s represented by a neural network, and hence can bescaled to datasets with an effectively infinite number of rows and columns. Our method consistsin defining a loss function whose minimizer is the desired principal subspace, and constructing agradient estimate of this loss whose bias can be controlled.

2023-04-11

Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (publié)

Investigating Multi-task Pretraining and Generalization in Reinforcement Learning

Adrien Ali Taiga

Jesse Farebrother

Google Brain

2023-02-01

ICLR.cc/2023/Conference (poster)

Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks

Jesse Farebrother

Joshua Greaves

Charline Le Lan

Ross Goroshin

Auxiliary tasks improve the representations learned by deep reinforcement learning agents. Analytically, their effect is reasonably well-und… (voir plus)erstood; in practice, how-ever, their primary use remains in support of a main learning objective, rather than as a method for learning representations. This is perhaps surprising given that many auxiliary tasks are defined procedurally, and hence can be treated as an essentially infinite source of information about the environment. Based on this observation, we study the effectiveness of auxiliary tasks for learning rich representations, focusing on the setting where the number of tasks and the size of the agent’s network are simultaneously increased. For this purpose, we derive a new family of auxiliary tasks based on the successor measure. These tasks are easy to implement and have appealing theoretical properties. Combined with a suitable off-policy learning rule, the result is a representation learning algorithm that can be understood as extending Mahadevan & Maggioni (2007)’s proto-value functions to deep reinforcement learning – accordingly, we call the resulting object proto-value networks. Through a series of experiments on the Arcade Learning Environment, we demonstrate that proto-value networks produce rich features that may be used to obtain performance comparable to established algorithms, using only linear approximation and a small number (~4M) of interactions with the environment’s reward function.

2023-02-01

ICLR.cc/2023/Conference (poster)

Bigger, Better, Faster: Human-level Atari with human-level efficiency

Max Schwarzer

Johan Samir Obando Ceron

We introduce a value-based RL agent, which we call BBF, that achieves super-human performance in the Atari 100K benchmark. BBF relies on sca… (voir plus)ling the neural networks used for value estimation, as well as a number of other design choices that enable this scaling in a sample-efficient manner. We conduct extensive analyses of these design choices and provide insights for future work. We end with a discussion about updating the goalposts for sample-efficient RL research on the ALE. We make our code and data publicly available at https://github.com/google-research/google-research/tree/master/bigger_better_faster.

2023-01-01

ICML (publié)

The Dormant Neuron Phenomenon in Deep Reinforcement Learning

Ghada Sokar

Utku Evci

In this work we identify the dormant neuron phenomenon in deep reinforcement learning, where an agent's network suffers from an increasing n… (voir plus)umber of inactive neurons, thereby affecting network expressivity. We demonstrate the presence of this phenomenon across a variety of algorithms and environments, and highlight its effect on learning. To address this issue, we propose a simple and effective method (ReDo) that Recycles Dormant neurons throughout training. Our experiments demonstrate that ReDo maintains the expressive power of networks by reducing the number of dormant neurons and results in improved performance.

2023-01-01

ICML (publié)

DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization

Aviral Kumar

Tengyu Ma

George Tucker

Sergey Levine

Despite overparameterization, deep networks trained via supervised learning are surprisingly easy to optimize and exhibit excellent generali… (voir plus)zation. One hypothesis to explain this is that overparameterized deep networks enjoy the benefits of implicit regularization induced by stochastic gradient descent, which favors parsimonious solutions that generalize well on test inputs. It is reasonable to surmise that deep reinforcement learning (RL) methods could also benefit from this effect. In this paper, we discuss how the implicit regularization effect of SGD seen in supervised learning could in fact be harmful in the offline deep RL setting, leading to poor generalization and degenerate feature representations. Our theoretical analysis shows that when existing models of implicit regularization are applied to temporal difference learning, the resulting derived regularizer favors degenerate solutions with excessive aliasing, in stark contrast to the supervised learning case. We back up these findings empirically, showing that feature representations learned by a deep network value function trained via bootstrapping can indeed become degenerate, aliasing the representations for state-action pairs that appear on either side of the Bellman backup. To address this issue, we derive the form of this implicit regularizer and, inspired by this derivation, propose a simple and effective explicit regularizer, called DR3, that counteracts the undesirable effects of this implicit regularizer. When combined with existing offline RL methods, DR3 substantially improves performance and stability, alleviating unlearning in Atari 2600 games, D4RL domains, and robotic manipulation from images.

2022-01-28

ICLR.cc/2022/Conference (spotlight)

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

Max Schwarzer

Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning

Marlos C. Machado

Reinforcement learning methods trained on few environments rarely learn policies that generalize to unseen environments. To improve generali… (voir plus)zation, we incorporate the inherent sequential structure in reinforcement learning into the representation learning process. This approach is orthogonal to recent approaches, which rarely exploit this structure explicitly. Specifically, we introduce a theoretically motivated policy similarity metric (PSM) for measuring behavioral similarity between states. PSM assigns high similarity to states for which the optimal policies in those states as well as in future states are similar. We also present a contrastive representation learning procedure to embed any state similarity metric, which we instantiate with PSM to obtain policy similarity embeddings (PSEs). We demonstrate that PSEs improve generalization on diverse benchmarks, including LQR with spurious correlations, a jumping task from pixels, and Distracting DM Control Suite.

2021-01-01

ICLR (publié)

Deep Reinforcement Learning at the Edge of the Statistical Precipice

Max Schwarzer

Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing their relative performance on a large suite of tasks. M… (voir plus)ost published results on deep RL benchmarks compare point estimates of aggregate performance such as mean and median scores across tasks, ignoring the statistical uncertainty implied by the use of a finite number of training runs. Beginning with the Arcade Learning Environment (ALE), the shift towards computationally-demanding benchmarks has led to the practice of evaluating only a small number of runs per task, exacerbating the statistical uncertainty in point estimates. In this paper, we argue that reliable evaluation in the few run deep RL regime cannot ignore the uncertainty in results without running the risk of slowing down progress in the field. We illustrate this point using a case study on the Atari 100k benchmark, where we find substantial discrepancies between conclusions drawn from point estimates alone versus a more thorough statistical analysis. With the aim of increasing the field's confidence in reported results with a handful of runs, we advocate for reporting interval estimates of aggregate performance and propose performance profiles to account for the variability in results, as well as present more robust and efficient aggregate metrics, such as interquartile mean scores, to achieve small uncertainty in results. Using such statistical tools, we scrutinize performance evaluations of existing algorithms on other widely used RL benchmarks including the ALE, Procgen, and the DeepMind Control Suite, again revealing discrepancies in prior comparisons. Our findings call for a change in how we evaluate performance in deep RL, for which we present a more rigorous evaluation methodology, accompanied with an open-source library rliable, to prevent unreliable results from stagnating the field. This work received an outstanding paper award at NeurIPS 2021.

Revisiting Fundamentals of Experience Replay

William Fedus

Prajit Ramachandran