nathangrinsztajn / Box-WorldLinks
Implementation of the Box-World environment from the paper "Relational Deep Reinforcement Learning"
☆47Updated last year
Alternatives and similar repositories for Box-World
Users that are interested in Box-World are comparing it to the libraries listed below
Sorting:
- Invariant Causal Prediction for Block MDPs☆44Updated 5 years ago
- This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the …☆89Updated 4 years ago
- ☆87Updated last year
- This repository contains code for the method and experiments of the paper "Learning with AMIGo: Adversarially Motivated Intrinsic Goals".☆63Updated last year
- Options of Interest: Temporal Abstraction with Interest Functions AAAI 2020☆25Updated 5 years ago
- Code accompanying the paper "Better Exploration with Optimistic Actor Critic" (NeurIPS 2019)☆68Updated 2 years ago
- ☆43Updated 6 years ago
- Efficient Exploration via State Marginal Matching (2019)☆69Updated 6 years ago
- Automatic Data-Regularized Actor-Critic (Auto-DrAC)☆102Updated 2 years ago
- ☆62Updated 7 years ago
- Revisiting Rainbow☆75Updated 4 years ago
- Soft Actor-Critic☆153Updated 7 years ago
- E-MAML, and RL-MAML baseline implemented in Tensorflow v1☆16Updated 5 years ago
- ☆114Updated 2 years ago
- impact-driven-exploration☆132Updated last year
- Estimating Q(s,s') with Deep Deterministic Dynamics Gradients☆32Updated 5 years ago
- A3C style Option-Critic with deliberation cost☆39Updated 7 years ago
- ☆31Updated 6 years ago
- Code release for Learning with Opponent-Learning Awareness and variations.☆149Updated 2 years ago
- ☆30Updated 2 years ago
- Pytorch implementation of "FeUdal Networks for Hierarchical Reinforcement Learning" for Montezuma's Revenge☆96Updated 3 years ago
- Library to compare and evaluate reward functions☆67Updated last year
- krazy grid world☆25Updated 5 years ago
- A Tensorflow implementation of the Option-Critic Architecture☆71Updated 8 years ago
- Easy MDPs and grid worlds with accessible transition dynamics to do exact calculations☆49Updated 3 years ago
- ☆112Updated 5 years ago
- MetaGenRL, a novel meta reinforcement learning algorithm. Unlike prior work, MetaGenRL can generalize to new environments that are entire…☆67Updated 5 years ago
- ☆106Updated last year
- OPE Tools based on Empirical Study of Off Policy Policy Estimation paper.☆61Updated 3 years ago
- ☆84Updated 4 years ago