schmidtdominik / Rainbow
Rainbow DQN implementation accompanying the paper "Fast and Data-Efficient Training of Rainbow" which reaches 205.7 median HNS after 10M frames. 🌈
☆45Updated 3 years ago
Alternatives and similar repositories for Rainbow:
Users that are interested in Rainbow are comparing it to the libraries listed below
- Docker containers of baseline agents for the Crafter environment☆28Updated 3 years ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆100Updated 2 years ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆54Updated 2 years ago
- ☆44Updated last year
- Synchronized Curriculum Learning for RL Agents☆45Updated last month
- Baselines for gymnax 🤖☆66Updated 2 years ago
- SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning☆14Updated 2 years ago
- ☆31Updated 4 years ago
- ☆42Updated 2 years ago
- ☆43Updated 7 months ago
- ☆41Updated 3 years ago
- Implementation of Tactical Optimistic and Pessimistic value estimation☆25Updated last year
- Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023☆19Updated last year
- Revisiting Rainbow☆74Updated 3 years ago
- ☆18Updated 2 months ago
- Challenging Memory-based Deep Reinforcement Learning Agents☆97Updated 5 months ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆52Updated last year
- ☆47Updated 2 years ago
- Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"☆23Updated last year
- Accelerated replay buffers in JAX☆41Updated 2 years ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆111Updated 8 months ago
- ☆76Updated last month
- Deep Reinforcement Learning Framework done with PyTorch☆35Updated last month
- A collection of matrix games in JAX☆10Updated 4 months ago
- Implementation of Diversity Is All You Need (DIAYN) on top of Stable Baselines 3.☆12Updated 2 years ago
- Skeleton for scalable and flexible Jax RL implementations☆80Updated last year
- Official code for "Pretraining Representations For Data-Efficient Reinforcement Learning" (NeurIPS 2021)☆54Updated 3 years ago
- This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the …☆83Updated 3 years ago
- Learning diverse options through the Laplacian representation.☆23Updated last year
- Vectorization techniques for fast population-based training.☆55Updated 2 years ago