MarcoMeter / endless-memory-gymLinks
Challenging Memory-based Deep Reinforcement Learning Agents
☆103Updated 9 months ago
Alternatives and similar repositories for endless-memory-gym
Users that are interested in endless-memory-gym are comparing it to the libraries listed below
Sorting:
- Evaluating long-term memory of reinforcement learning algorithms☆146Updated 2 years ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆180Updated 5 months ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆100Updated 3 years ago
- Benchmarking RL generalization in an interpretable way.☆161Updated 2 months ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆114Updated last year
- Deep Hierarchical Planning from Pixels☆107Updated 2 years ago
- ☆82Updated 5 months ago
- ☆48Updated 2 years ago
- Partially Observable Process Gym☆197Updated 2 months ago
- Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.☆133Updated last year
- Object Centric Atari games☆88Updated last month
- Extreme Q-Learning: Max Entropy RL without Entropy☆86Updated 2 years ago
- Synthetic Experience Replay☆99Updated last year
- Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)☆75Updated 2 years ago
- Reproduction of Dreamerv1 and v2 in pytorch for deepmind control suite☆43Updated 2 years ago
- Baselines for gymnax 🤖☆71Updated 2 years ago
- ExORL: Exploratory Data for Offline Reinforcement Learning☆115Updated 3 years ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆52Updated 2 years ago
- Contains JAX implementation of algorithms for inverse reinforcement learning☆73Updated last year
- Unified Implementations of Offline Reinforcement Learning Algorithms☆89Updated 4 months ago
- Datasets for data-driven deep reinforcement learning with Atari (wrapper for datasets released by Google)☆120Updated 11 months ago
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆108Updated 2 months ago
- ☆43Updated 2 years ago
- [NeurIPS 2022] Open source code for reusing prior computational work in RL.☆97Updated 2 years ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆58Updated 3 years ago
- Implementation of Trajectory Transformer with attention caching and batched beam search☆115Updated 2 years ago
- Foundation Policies with Hilbert Representations (ICML 2024)☆91Updated last year
- ☆103Updated 6 months ago
- When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment, NeurIPS 2023 (oral)☆64Updated last year
- Code for "SimbaV2: Hyperspherical Normalization for Scalable Deep Reinforcement Learning"☆63Updated 2 months ago