schmidtdominik / Rainbow
Rainbow DQN implementation accompanying the paper "Fast and Data-Efficient Training of Rainbow" which reaches 205.7 median HNS after 10M frames. 🌈
☆43Updated 2 years ago
Related projects: ⓘ
- Vectorization techniques for fast population-based training.☆52Updated 2 years ago
- Docker containers of baseline agents for the Crafter environment☆27Updated 2 years ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆49Updated 2 years ago
- ☆27Updated 3 years ago
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆76Updated last year
- ☆25Updated last week
- Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"☆22Updated last year
- This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the …☆83Updated 3 years ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆46Updated last year
- ☆35Updated 2 years ago
- ☆41Updated 5 months ago
- ☆34Updated last year
- Repository for the QDgym code. A framework for Quality Diversity optimization benchmark tasks based OpenAI Gym.☆21Updated 3 years ago
- Repository for the PGA-MAP-Elites algorithm. PGA-MAP-Elites was developed to efficiently scale MAP-Elites to large genotypes and noisy d…☆35Updated 2 years ago
- Accelerated replay buffers in JAX☆39Updated 2 years ago
- 🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX☆46Updated 10 months ago
- Implementation of Tactical Optimistic and Pessimistic value estimation☆24Updated last year
- Simple implementation of V-MPO proposed in https://arxiv.org/abs/1909.12238☆44Updated 3 years ago
- ☆37Updated last year
- AGAC: Adversarially Guided Actor-Critic☆47Updated 3 years ago
- Official code for "Pretraining Representations For Data-Efficient Reinforcement Learning" (NeurIPS 2021)☆51Updated 3 years ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆96Updated 2 years ago
- When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment, NeurIPS 2023 (oral)☆49Updated 8 months ago
- SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning☆13Updated last year
- ☆56Updated last month
- ☆21Updated 2 years ago
- Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023☆16Updated 8 months ago
- Revisiting Rainbow☆73Updated 3 years ago
- Official code release for "CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity"☆53Updated 3 months ago
- An Open-Ended Agentic Simulator☆17Updated last month