Skip to main content

(#285) MuJoCo: CleanRL's TD3 + JAX

Created on October 20|Last edited on November 1

200k400k600k800kSteps02000400060008000Episodic Return
CleanRL's td3_continuous_action_jax.py (VM w/ TPU) #285
CleanRL's td3_continuous_action_jax.py (VM w/ TPU)
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI) #285
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI)
10203040Time (minutes)02000400060008000Episodic Return
CleanRL's td3_continuous_action_jax.py (VM w/ TPU) #285
CleanRL's td3_continuous_action_jax.py (VM w/ TPU)
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI) #285
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI)
CleanRL's td3_continuous_action_jax.py (VM w/ TPU) #285
3
CleanRL's td3_continuous_action_jax.py (VM w/ TPU)
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI) #285
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI)
3



CleanRL's td3_continuous_action_jax.py (VM w/ TPU) #285
3
CleanRL's td3_continuous_action_jax.py (VM w/ TPU)
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI) #285
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI)
6



CleanRL's td3_continuous_action_jax.py (VM w/ TPU) #285
3
CleanRL's td3_continuous_action_jax.py (VM w/ TPU)
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI) #285
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI)
6