General Reinforcement Learning
35 papers with code • 6 benchmarks • 7 datasets
Benchmarks
These leaderboards are used to track progress in General Reinforcement Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find General Reinforcement Learning models and implementations
ProcGen
Obstacle Tower
WLD
PackIt
Avalon
bipedal-skills
POPGym
Latest papers with no code
Dynamic Knowledge Injection for AIXI Agents
Prior approximations of AIXI, a Bayesian optimality notion for general reinforcement learning, can only approximate AIXI's Bayesian environment model using an a-priori defined set of models.
Dropout Strategy in Reinforcement Learning: Limiting the Surrogate Objective Variance in Policy Optimization Methods
Then, we introduced a general reinforcement learning framework applicable to mainstream policy optimization methods, and applied the dropout technique to the PPO algorithm to obtain the D-PPO variant.
Image Transformation Sequence Retrieval with General Reinforcement Learning
In this work, the novel Image Transformation Sequence Retrieval (ITSR) task is presented, in which a model must retrieve the sequence of transformations between two given images that act as source and target, respectively.
L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning
Tasks that involve interaction with various targets are called multi-target tasks.
Computably Continuous Reinforcement-Learning Objectives are PAC-learnable
In particular, for the analysis that considers only sample complexity, we prove that if an objective given as an oracle is uniformly continuous, then it is PAC-learnable.
Policy Mirror Descent Inherently Explores Action Space
SPMD with the second evaluation operator, namely truncated on-policy Monte Carlo (TOMC), attains an $\tilde{\mathcal{O}}(\mathcal{H}_{\mathcal{D}}/\epsilon^2)$ sample complexity, where $\mathcal{H}_{\mathcal{D}}$ mildly depends on the effective horizon and the size of the action space with properly chosen Bregman divergence (e. g., Tsallis divergence).
Computational Dualism and Objective Superintelligence
This undermines claims regarding the behaviour of theorised, software superintelligence.
Accuracy-Guaranteed Collaborative DNN Inference in Industrial IoT via Deep Reinforcement Learning
Specifically, sampling rate adaption, inference task offloading and edge computing resource allocation are jointly considered to minimize the average service delay while guaranteeing the long-term accuracy requirements of different inference services.
AcceRL: Policy Acceleration Framework for Deep Reinforcement Learning
Inspired by the redundancy of neural networks, we propose a lightweight parallel training framework based on neural network compression, AcceRL, to accelerate the policy learning while ensuring policy quality.
Computable Artificial General Intelligence
AIXI appears to be the only such formalism supported by proof that its behaviour is optimal, a consequence of its use of compression as a proxy for intelligence.
