Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning

• URL: http://arxiv.org/abs/2404.03774v1
• Date: Thu, 4 Apr 2024 19:35:41 GMT
• Title: Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning
• Authors: Noah Golowich, Ankur Moitra, Dhruv Rohatgi,
• Abstract summary: We show the first cryptographic separation between reinforcement learning and supervised learning. We also show that there is no computationally efficient algorithm for reward-directed RL in block MDPs.
• Score: 34.791182995710024
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Supervised learning is often computationally easy in practice. But to what extent does this mean that other modes of learning, such as reinforcement learning (RL), ought to be computationally easy by extension? In this work we show the first cryptographic separation between RL and supervised learning, by exhibiting a class of block MDPs and associated decoding functions where reward-free exploration is provably computationally harder than the associated regression problem. We also show that there is no computationally efficient algorithm for reward-directed RL in block MDPs, even when given access to an oracle for this regression problem. It is known that being able to perform regression in block MDPs is necessary for finding a good policy; our results suggest that it is not sufficient. Our separation lower bound uses a new robustness property of the Learning Parities with Noise (LPN) hardness assumption, which is crucial in handling the dependent nature of RL data. We argue that separations and oracle lower bounds, such as ours, are a more meaningful way to prove hardness of learning because the constructions better reflect the practical reality that supervised learning by itself is often not the computational bottleneck.

Related papers

• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Hybrid Inverse Reinforcement Learning [34.793570631021005]
  inverse reinforcement learning approach to imitation learning is a double-edged sword. We propose using hybrid RL -- training on a mixture of online and expert data -- to curtail unnecessary exploration. We derive both model-free and model-based hybrid inverse RL algorithms with strong policy performance guarantees.
  arXiv  Detail & Related papers  (2024-02-13T23:29:09Z)
• The Virtues of Pessimism in Inverse Reinforcement Learning [38.98656220917943]
  Inverse Reinforcement Learning is a powerful framework for learning complex behaviors from expert demonstrations. It is desirable to reduce the exploration burden by leveraging expert demonstrations in the inner-loop RL. We consider an alternative approach to speeding up the RL in IRL: emphpessimism, i.e., staying close to the expert's data distribution, instantiated via the use of offline RL algorithms.
  arXiv  Detail & Related papers  (2024-02-04T21:22:29Z)
• The Effective Horizon Explains Deep RL Performance in Stochastic Environments [21.148001945560075]
  Reinforcement learning (RL) theory has largely focused on proving mini complexity sample bounds. We introduce a new RL algorithm, SQIRL, that iteratively learns a nearoptimal policy by exploring randomly to collect rollouts. We leverage SQIRL to derive instance-dependent sample complexity bounds for RL that are exponential only in an "effective horizon" look-ahead and on the complexity of the class used for approximation.
  arXiv  Detail & Related papers  (2023-12-13T18:58:56Z)
• RvS: What is Essential for Offline RL via Supervised Learning? [77.91045677562802]
  Recent work has shown that supervised learning alone, without temporal difference (TD) learning, can be remarkably effective for offline RL. In every environment suite we consider simply maximizing likelihood with two-layer feedforward is competitive. They also probe the limits of existing RvS methods, which are comparatively weak on random data.
  arXiv  Detail & Related papers  (2021-12-20T18:55:16Z)
• Exploratory State Representation Learning [63.942632088208505]
  We propose a new approach called XSRL (eXploratory State Representation Learning) to solve the problems of exploration and SRL in parallel. On one hand, it jointly learns compact state representations and a state transition estimator which is used to remove unexploitable information from the representations. On the other hand, it continuously trains an inverse model, and adds to the prediction error of this model a $k$-step learning progress bonus to form the objective of a discovery policy.
  arXiv  Detail & Related papers  (2021-09-28T10:11:07Z)
• Simplifying Deep Reinforcement Learning via Self-Supervision [51.2400839966489]
  Self-Supervised Reinforcement Learning (SSRL) is a simple algorithm that optimize policies with purely supervised losses. We show that SSRL is surprisingly competitive to contemporary algorithms with more stable performance and less running time.
  arXiv  Detail & Related papers  (2021-06-10T06:29:59Z)
• DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction [96.90215318875859]
  We show that bootstrapping-based Q-learning algorithms do not necessarily benefit from corrective feedback. We propose a new algorithm, DisCor, which computes an approximation to this optimal distribution and uses it to re-weight the transitions used for training.
  arXiv  Detail & Related papers  (2020-03-16T16:18:52Z)
• Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning [96.78504087416654]
  Motivated by the prevailing paradigm of using unsupervised learning for efficient exploration in reinforcement learning (RL) problems, we investigate when this paradigm is provably efficient. We present a general algorithmic framework that is built upon two components: an unsupervised learning algorithm and a noregret tabular RL algorithm.
  arXiv  Detail & Related papers  (2020-03-15T19:23:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.