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
Related projects ⓘ
Alternatives and complementary repositories for level-replay
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆99Updated 2 years ago
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆79Updated last year
- ☆36Updated last year
- ExORL: Exploratory Data for Offline Reinforcement Learning☆105Updated 2 years ago
- Implementation of Tactical Optimistic and Pessimistic value estimation☆25Updated last year
- Estimating Q(s,s') with Deep Deterministic Dynamics Gradients☆32Updated 4 years ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆49Updated 2 years ago
- Revisiting Rainbow☆73Updated 3 years ago
- ☆54Updated 8 months ago
- Learning Action-Value Gradients in Model-based Policy Optimization☆31Updated 3 years ago
- Invariant Causal Prediction for Block MDPs☆43Updated 4 years ago
- Efficient Exploration via State Marginal Matching (2019)☆66Updated 5 years ago
- Pytorch implementations of RL algorithms, focusing on model-based, lifelong, reset-free, and offline algorithms. Official codebase for Re…☆98Updated 2 years ago
- AGAC: Adversarially Guided Actor-Critic☆47Updated 3 years ago
- Learning Laplacian Representations in Reinforcement Learning☆17Updated 3 years ago
- ☆81Updated 3 years ago
- A collection of RL algorithms written in JAX.☆95Updated 2 years ago
- Disagreement-Regularized Imitation Learning☆30Updated 3 years ago
- Implementation of Bootstrap DQN and Randomized Prior Functions on ALE☆52Updated 5 years ago
- Maximum Entropy-Regularized Multi-Goal Reinforcement Learning (ICML 2019)☆23Updated 5 years ago
- Code for "Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills"☆36Updated 4 years ago
- Code for the paper "Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction"☆42Updated last year
- CaDM: Context-aware Dynamics Model for Generalization in Model-based Reinforcement Learning☆63Updated 4 years ago
- Options of Interest: Temporal Abstraction with Interest Functions AAAI 2020☆25Updated 4 years ago
- RE3: State Entropy Maximization with Random Encoders for Efficient Exploration☆67Updated 3 years ago
- ☆30Updated last year
- On the model-based stochastic value gradient for continuous reinforcement learning☆55Updated last year
- ☆110Updated last year
- ☆29Updated 5 years ago
- Proto-RL: Reinforcement Learning with Prototypical Representations☆82Updated 2 years ago