facebookresearch / level-replay
This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the fact that not all levels are equally useful for agents to learn from during training.
☆83Updated 3 years ago
Alternatives and similar repositories for level-replay:
Users that are interested in level-replay are comparing it to the libraries listed below
- ☆44Updated last year
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆80Updated 2 years ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆100Updated 2 years ago
- Revisiting Rainbow☆74Updated 3 years ago
- Implementation of Tactical Optimistic and Pessimistic value estimation☆25Updated last year
- RE3: State Entropy Maximization with Random Encoders for Efficient Exploration☆68Updated 3 years ago
- Invariant Causal Prediction for Block MDPs☆44Updated 4 years ago
- This repository contains code for the method and experiments of the paper "Learning with AMIGo: Adversarially Motivated Intrinsic Goals".☆61Updated last year
- CaDM: Context-aware Dynamics Model for Generalization in Model-based Reinforcement Learning