p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

5938 stars · 1204 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A collection of PyTorch implementations of deep reinforcement learning algorithms (DQN, PPO, SAC, TD3, DDPG, A3C, HER, hierarchical RL) with accompanying environments. It serves primarily as an educational reference for studying and comparing RL algorithm implementations.

Use cases

• learn how DQN and its variants are implemented in PyTorch
• study reference implementations of PPO and SAC
• compare different deep RL algorithms side by side
• find a starting point for implementing a custom RL agent
• understand hindsight experience replay and hierarchical RL
• teach a reinforcement learning course with working code examples

When to choose

• you want readable, well-documented implementations of classic deep RL algorithms
• you are learning reinforcement learning and want code alongside the papers
• you need a reference to check your own RL implementation against

When to avoid

• you need a production-grade, high-performance RL training framework
• you want the latest algorithms with active development and community support
• you need distributed or large-scale RL training at scale

Facets

learning-resource · maturity maintenance

machine-learning reinforcement-learning deep-learning reinforcement-learning machine-learning tutorials python cross-platform pytorch dqn ppo sac td3 actor-critic educational reference-implementations

Member repositories

For agents

markdown · JSON · MCP: product_card(name="p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch")